DESC:EARLIEST PRIORITY DATE:
This application claims priority from a provisional patent application filed in India having patent application no. 202431005047, filed on January 24, 2024, and titled “EFFICIENCY EVALUATION COMBINING ECONOMIC MODELLING AND TESSELLATION AUGMENTED VIA NEURAL NETWORKS FOR RETAIL SECTOR APPLICATION”.
FIELD OF INVENTION
[0001] Embodiments of the present disclosure relate to the field of retail chain of a business, and more particularly to a system and method for evaluating efficiency of a multi-brand retail chain and determining benchmarks.
BACKGROUND
[0002] Measuring operational efficiency is crucial for the success of every business. It helps decision makers to identify areas for improvement, increase productivity, improve customer experience and gain a competitive advantage. Today, several techniques exist to evaluate a retail store’s productivity, and its relative efficiency involves evaluating many factors - such as sales turnover, sales per floor space, employee productivity, customer traffic, catchment area, gross margin, among other factors. Generally, in most businesses, store efficiency is evaluated by considering a ratio of two metrics (for instance, sales per floor space or customer per employee and so on) and other suitable ratios.
[0003] A retail chain that has multiple stores faces several challenges in measuring and improving efficiency in a multi-brand retail chain with so many different outcome and input metrics especially when aiming for sustainability goals and ensuring decisions are equitable and explainable. Typically, for a retail chain, efficiency may be defined as a ratio of the outputs (for instance, sales, profit) of a business process to the inputs (for instance, labour, inventory) provided. However, with multiple inputs and outputs, computing efficiency becomes a complicated scientific process. Further, it is important to note that for a multi-brand retail chain of stores, the demographic data which includes catchment area and derived Serviceable Addressable Market (SAM) in terms of potential customers is critical to evaluate a store’s performance when combined with different combination of output metrics of sales volume/value, unique acquired customers and so on.
[0004] Moreover, different format stores have different levels of inputs and cannot be compared at par from outcome perspective. This makes it difficult to use a single, straightforward formula to measure and compare the efficiency of all stores. Consequently, this in turn prevents management from comparing and identifying underperforming business units and take remedial measures or allocate or redistribute resources for long-term efficiency gain. Additionally, without a reliable method to compare stores, management may struggle to identify underperforming stores and make informed decisions about resource allocation or improvements.
[0005] However, because of issues like subjectivity and the lack of a clear, unified system that includes both (using geometry to estimate SAM and combining it with advanced economic modelling methods) it is difficult to assess efficiency and set a benchmark for a multi-brand retail chain company.
[0006] Also, in the world of data science-based business solutions using advanced algorithms, explainability is posing a challenge for different stakeholders while using advanced algorithms. This in turn poses a challenge in customer confidence in terms of reliability of predictions. There is no standard framework available to address this challenge for efficiency evaluation for multi-category multi-brand retail chain businesses.
[0007] Hence, there is a need for an improved system and method for evaluating efficiency of a multi-brand retail chain and determining benchmarks which addresses the aforementioned issue(s).
OBJECTIVE OF THE INVENTION
[0008] An objective of the present invention is to provide a comprehensive framework to evaluate efficiency of a multi-brand retail chain and determine benchmarks using a combination of computational geometry and economic modelling.
[0009] Another objective of the present invention is to combine seamlessly Voronoi Tessellation and Data Envelopment Analysis (DEA) into one framework. The first step of using Tessellation method is to compute the intermediate input of Serviceable Addressable Market (SAM) which is consumed by DEA as one of the many input parameters in the subsequent step.
[0010] Another objective of the present invention is to use multiple input and output parameters to compute store efficiency dynamically by the DEA. One of the multiple inputs is SAM as derived from Tessellation.
[0011] Yet another objective of the present invention is to validate DEA outcomes using a prediction model of a neural network thereby benchmarking and improving store efficiency.
BRIEF DESCRIPTION
[0012] In accordance with an embodiment of the present disclosure, a system for evaluating efficiency of a multi-brand retail chain and determining benchmarks is provided. The system includes a processing subsystem hosted on a server and configured to execute on a network to control communications among a plurality of modules. The plurality of modules includes an input metrices identification module, a computational module, an output metrics identification module and an efficiency computation module. The input metrices identification module is configured to receive a plurality of inputs from a business organization wherein the plurality of inputs includes a plurality of input parameters and a plurality of output parameters of the business.. The computational module is configured to estimate a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers. The computational module is configured to map the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area. Further, the computational module is configured to compute a Serviceable Addressable Market value for each of the multiple stores using a geometrical computation to determine one or more operational factors. The output metrics identification module operatively coupled to the input metrics identification module wherein the output metrics identification module is configured to utilize a sales turnover and a number of acquired customers as outputs. The efficiency computation module operatively coupled to the output metrics identification module and the input metric identification module wherein the efficiency computation module is configured to estimate a relative efficiency for each store wherein a score of one as the relative efficiency indicates optimal efficiency.
[0013] In accordance with another embodiment of the present disclosure, a method for evaluating efficiency of a multi-brand retail chain and determining benchmarks is provided. The method includes receiving, by an input metrics identification module, a plurality of inputs from a business organization wherein the plurality of inputs includes a plurality of input parameters and a plurality of output parameters of the business. The method includes estimating, by a computational module, a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers. The method includes mapping, by the computational module, the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area. The method includes computing, by the computational module, a Serviceable Addressable Market value for each of the multiple stores using a geometrical computation to determine one or more operational factors. Furthermore, the method includes utilizing, by an output metrics identification module, a sales turnover and a number of acquired customers as outputs. Moreover, the method includes estimating, by an efficiency computation module, a relative efficiency for each store wherein a score of one as the relative efficiency indicates optimal efficiency.
[0014] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0016] FIG. 1 is a block diagram representation of a system for evaluating efficiency of a multi-brand retail chain and determining benchmarks, in accordance with an embodiment of the present disclosure;
[0017] FIG. 2 is a block diagram representing an exemplary embodiment of the system of FIG. 1 in accordance with an embodiment of the present disclosure;
[0018] FIG. 3 is an exemplary graphical representation of a frontier curve plotted by joining data points representing the efficiency of FIG. 1 in accordance with an embodiment of the present disclosure;
[0019] FIG. 4 is a block diagram of a computer or a server in accordance with an embodiment of the present disclosure; and
[0020] FIG. 5 illustrates a flow chart representing the steps involved in a method for evaluating efficiency of a multi-brand retail chain and determining benchmarks in accordance with an embodiment of the present disclosure.
[0021] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0022] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0023] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or subsystems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0025] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[0026] In accordance with an embodiment of the present disclosure, a system for evaluating efficiency of a multi-brand retail chain and determining benchmarks is provided. The system includes a processing subsystem hosted on a server and configured to execute on a network to control communications among a plurality of modules. The plurality of modules includes an input metrices identification module, a computational module, an output metrics identification module and an efficiency computation module. The input metrices identification module is configured to receive a plurality of inputs from a business organization wherein the plurality of inputs includes a plurality of input parameters and a plurality of output parameters of the business. The computational module is configured to estimate a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers. The computational module is configured to map the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area. Further, the computational module is configured to compute a Serviceable Addressable Market value for each of the multiple stores using a geometrical computation to determine one or more operational factors. The output metrics identification module operatively coupled to the input metrics identification module wherein the output metrics identification module is configured to utilize a sales turnover and a number of acquired customers as outputs. The efficiency computation module operatively coupled to the output metrics identification module and the input metric identification module wherein the efficiency computation module is configured to estimate a relative efficiency score for each store using a Data Envelopment Analysis, the computed Serviceable Addressable Market value and the plurality of input parameters and output parameters wherein a score of one as the relative efficiency indicates optimal efficiency.
[0027] FIG. 1 is a block diagram representation of a system for evaluating efficiency of a multi-brand retail chain and determining benchmarks, in accordance with an embodiment of the present disclosure. The system (100) includes a processing subsystem (105) hosted on a server (110). In one embodiment, the server (110) may include a cloud server. In another embodiment, the server (110) may include a local server. The processing subsystem (105) is configured to execute on a network (115) to control communications among a plurality of modules. In a preferred embodiment, the network (115) may include a Wireless local area network (WLAN) network, a cellular network and a Low-power wide-area (LPWA) network. In one embodiment, the network (115) may also include a wired network such as local area network (LAN), Wi-Fi, Bluetooth, Zigbee, near field communication (NFC), infra-red communication (RFID) or the like. Further, the plurality of modules includes an input metrics identification module (120), a computational module (125), an output metrics identification module (130) and an efficiency computation module (135).
[0028] The input metrics identification module (120) is configured to receive a plurality of inputs from a business organization wherein the plurality of inputs includes a plurality of input parameters and a plurality of output parameters of the business. Examples of the plurality of input parameters includes, but is not limited to, a store floor space, stock-keeping unit and number of promotional stalls. Examples of the plurality of output parameters includes, but is not limited to, revenue per customer and total number of customers. The business organization refers to a multi-brand retail setting. The store floor space defines the physical space of the store. Further, the stock-keeping retail setting is a unique identifier for each product or item in the store’s inventory. The promotional stalls are typically the display areas for special promotions in the store.
[0029] The computational module (125) is operatively coupled to the input metrics identification module. The computational module (125) is configured to estimate a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers. In other words, the catchment area refers to the geographic zone surrounding a store from which it draws or attracts customers. Essentially, it’s the area where most of the store’s customers are likely to come from.
[0030] Further, the computational module (125) is configured to map the catchment area with a corresponding census data pertaining to the geographical locations. The mapping involves integrating the catchment area with relevant census data. In one embodiment, the census data includes information about the population, such as demographics, income levels, age distribution, and more, based on specific geographical locations. The census data used is specifically related to the geographical areas that fall within the catchment area. Further, the mapping generates a Geographical Information System (GIS) for each store to estimate a population residing in the said mapped catchment area. A GIS is a tool that visualizes and analyses geographical data, allowing for the examination of patterns, relationships, and trends in the data. The purpose of creating this GIS is to estimate the number of people (population) living within the mapped catchment area. This gives the business organization a clearer understanding of the potential customer base in the vicinity of each store.
[0031] Furthermore, the computational module (125) is configured to compute a Serviceable Addressable Market (SAM) value for each of the multiple stores using a geometrical computation to determine one or more operational factors. Typically, the SAM value is a key business metric. The SAM value refers to the portion of the overall market that a business organization can realistically target and serve with its products or services. Further, the SAM value is computed individually for each store, meaning the module assesses the potential market for each specific store location. The computational module (125) uses a mathematical technique, particularly geometrical calculations, to determine the SAM value. This might involve spatial analysis or other forms of geometrical modelling to understand the market in terms of size, shape, and other spatial relationships. These geometrical computations help the module assess certain operational factors that influence the SAM value. Operational factors might include things like store accessibility, proximity to key customer segments, or the layout of the store relative to the population in the catchment area.
[0032] The geometric computation that is used is called as Voronoi Tessellation to estimate the catchment area for each store based on Euclidean distance. Typically, Voronoi Tessellation refers to a way of dividing a plane into regions based on the distance between a set of seed points. Given a set of seed points in a plane, the Voronoi Tessellation partitions the plane into polygonal cells, with each cell being associated with a unique seed point. The cell of a seed point consists of all points in the plane that are closer to that seed point than to any other seed point. In other words, the Voronoi Tessellation creates a mapping between each seed point and the region of the plane closest to it.
[0033] The resulting tiled regions of the Voronoi Tessellation are often referred to as Voronoi diagrams. These diagrams are used in a variety of fields, including computer science, geography, and engineering. For example, they can be used to model the distribution of resources, such as water or food, in a landscape, or to understand the patterns of communication between individuals in a social network.
[0034] The Voronoi tessellation can be visualized as a partition of the space into cells, with each cell representing the Voronoi cell of a single point in X. In summary, Voronoi tessellation is a mathematical concept that partitions a space into regions based on the proximity of points in the space. The Voronoi cell of a point xi is defined as the set of all points in the space that are closer to xi than to any other point in X.
[0035] It must be noted that the SAM is obtained from a Total Addressable Market (TAM). SAM is a more focused subset of that takes into account the businesses specific reach and operational capabilities.
[0036]
[0037] Additionally, the output metrics identification module (130) operatively coupled to the input metrics identification module wherein the output metrics identification module is configured to utilize a sales turnover and a number of acquired customers as outputs. The sales turnover refers to the total revenue generated by the business organization or a store within a specific period. It measures how much money the business organization is making from its sales. The other output is the number of acquired customers, which refers to the number of new customers the business organization has gained over a certain period. This metric is important for understanding customer growth and market penetration.
[0038] The efficiency computation module (135) operatively coupled to the output metrics identification module and the input metrics identification module wherein the efficiency computation module is configured to estimate a relative efficiency score for each store using a Data Envelopment Analysis, the computed Serviceable Addressable Market value and the plurality of input parameters and output parameters wherein a score of one as the relative efficiency indicates optimal efficiency. "Relative efficiency" means that the efficiency of each store is evaluated in comparison to other stores or a benchmark. The module assigns a score to each store based on its relative efficiency. A score of one (1) represents optimal efficiency, meaning that the store is operating as efficiently as possible according to the criteria used in the analysis. Scores below one would indicate less-than-optimal efficiency, suggesting room for improvement.
[0039] The SAM value, which the module previously calculated for each store, is used as a key input in the DEA. The SAM value provides important context, such as the size of the market each store can realistically serve, which is crucial for assessing how efficiently each store is operating relative to its market potential. Data envelopment analysis (DEA) is a non-parametric programming method that has been widely used in the retail sector for measuring the efficiency of decision-making units (DMUs). It provides a framework for comparing the performance of multiple DMUs based on a set of inputs and outputs and enables decision-makers to identify best practices and areas for improvement. The DEA is conducted across multiple stores within the business organization, meaning it evaluates and compares the performance of various stores against each other. DEA compares multiple units (stores) to identify which ones are operating most efficiently relative to others. DEA has been applied in various aspects of retail operations, including store management, supply chain management, and customer service, among others.
[0040] The point of departure for the calculation of efficiency measures is the piece-wise linear frontier technology expressed by the following production possibility set:

where, x is the input vector,
y is the output vector,
J are the observations,
m is the indexed output,
n is the input, and
[0041] ?j (j =1… J) are non-negative weights (intensity variables) defining frontier points.
[0042] FIG. 2 is a block diagram representing an exemplary embodiment of the system of FIG. 1 in accordance with an embodiment of the present disclosure. The system (100) further includes an artificial intelligence module (140), a benchmarking module (145) and an application module (150).
[0043] The artificial intelligence module (140) is operatively coupled to the efficiency computation module (135) and configured to predict efficiency of the multiple stores by an artificial intelligence model trained with a data set of store data. The AI module’s (140) main function is to predict the future efficiency of multiple stores. Instead of just calculating current efficiency, it uses AI to forecast how efficiently each store is likely to operate in the future. The AI module (140) makes these predictions using the AI model that has been trained on a dataset containing historical and possibly current data about the stores. This dataset might include various metrics, such as sales figures, customer numbers, operational costs, and past efficiency scores. The AI model learns patterns and relationships within this data, enabling it to make accurate predictions about future efficiency.
[0044] In one embodiment, the relative efficiency for each store is compared and fed as a training data set to the artificial intelligence module (140). The comparison of the relative efficiency to analyse differences between the plurality of stores or to establish benchmark. The AI module (140) uses this relative efficiency data to train its model. By learning from these efficiency scores, the AI model can better understand the factors that influence store efficiency and improve its ability to predict future efficiency.
[0045] The comparison is specifically focused on the efficiency values of each store. These efficiency values could be the current relative efficiency scores calculated by the efficiency computation module or predicted efficiency values generated by the AI module.
[0046] Further, the benchmarking module (145) operatively coupled to the artificial intelligence module (140) wherein the benchmarking module (145) is configured to compare the multiple stores based on efficiency values. The benchmarking module (145) is responsible for comparing the efficiency of multiple stores. It uses efficiency data, possibly including predictions made by the AI module (140), to determine how each store performs relative to others. This comparison helps the business organization to identify the most and least efficient stores, setting benchmarks for performance improvement.
[0047] Furthermore, the application module (150) operatively coupled to the benchmarking module (145) wherein the application module (150) is configured to utilize a plurality of technology stack. The application module (150) accesses the comparative data or insights generated by the benchmarking module (145). The application module (150) is designed to work with or incorporate a variety of technology stacks. A "technology stack" refers to the combination of programming languages, frameworks, tools, and software used to build and run applications. In one embodiment, the “technology stack” includes Python, Colab, GitHub and MySQL. The application module (150) integrates with different technologies to enable the system’s various features, possibly including user interfaces, data processing, and other operational functionalities.
[0048] Consider a non-limiting example wherein a large retail chain called "RetailX," operates in multiple stores across different cities, each selling a variety of brands. RetailX has a central server that hosts a processing subsystem. This system is connected to all the stores through a network, allowing for communication between the central system and the various modules within each store. The input metrics identification module (120) collects key data points from each store in the RetailX chain. The inputs are Store Floor Space (for example, Store A has 15,000 square feet), Stock-Keeping Unit (The number of different products each store carries, for example, Store A has 10,000 SKUs) and Number of Promotional Stalls (for example, Store A has 5 promotional stalls). The computational module (125) uses the data from the input metrics identification module to estimate the catchment area for each store. For example, for Store A, located in a busy urban area, the system (100) calculates that the store draws customers from a 5-mile radius. The catchment area with census data to create a Geographical Information System (GIS) for each store. For example, for Store A, the GIS shows that there are 200,000 people living within its catchment area, with an average household income of $50,000. Using geometric computations, the computational module (125) estimates the SAM value for each store. For Store A, considering factors like accessibility, customer demographics, and competition, the SAM is calculated as 120,000 potential customers. The computational module (125) performs a DEA to assess how efficiently each store is operating relative to its SAM. Store A is compared to other stores in the chain, and its efficiency is analysed based on its ability to convert the SAM into actual sales. The output metrics identification module (130) uses output data such as sales turnover and the number of new customers. Store A reports a monthly sales turnover of $1.5 million and has acquired 500 new customers in the past month. The efficiency computational module (135) module calculates the relative efficiency of each store based on the output data. The system determines that Store A has a relative efficiency score of 0.85, indicating that while it is performing well, there is room for improvement compared to other stores with a score closer to 1 (optimal efficiency).
[0049] To sum up, RetailX uses the described system (100) to gather detailed input data from each store, such as floor space and promotional activities, and then combines it with geographical and census data to evaluate the market potential (SAM) for each store. The system analyses sales and customer acquisition data to compute the efficiency of each store. The results help RetailX understand which stores are performing optimally and which ones may need operational adjustments to improve their efficiency and overall performance.
[0050] FIG. 3 is an exemplary graphical representation of a frontier curve plotted by joining data points representing the efficiency of FIG. 1 in accordance with an embodiment of the present disclosure.
[0051] The graph illustrates the customers (x100/day) Per Unit Floor Space (x10,000 sq. ft) on an X axis and sales (x$10, 000/day) per unit floor space (x10, 000 sq. Ft) on an Y axis. The efficiency frontier of multiple stores (302a, 302b, 302c, 302d and 302e) is depicted on a line (304) which is also referred to as the ‘frontier curve’. Typically, the efficiency of the multiple stores (302a, 302b, 302c, 302d and 302e) is 1 or close to 1 (based on different proportion of sales and customers). Further, multiple DMU’s of other stores are plotted on the graph (illustrated as ‘x’) based on their corresponding efficiency.
[0052] Typically, the graph illustrates the output between sales and customers per unit floor space. Considering that the efficiency relates to output maximization, the frontier curve is concave in nature (with respect to the origin). The line (304) illustrates a benchmark (DEA-envelope) that should be the target for the other multiple stores (‘x’) to reach and enhance their efficiency to 1. For instance, consider the store with efficiency plotted at (306). The line D is the full distance from the origin to the envelope. The line D’ represents the improvement for the store to grow and align with the envelope. Such way of representation and prediction enhances the efficiency of the stores.
[0053] FIG. 4 is a block diagram of a computer or a server (110) in accordance with an embodiment of the present disclosure. The server (110) includes processor(s) (210), and memory (220) operatively coupled to the bus (230). The processor(s) (210), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.
[0054] The memory (220) includes several subsystems stored in the form of executable program which instructs the processor (210) to perform the method steps illustrated in FIG. 1. The memory (220) includes a processing subsystem (105) of FIG.1. The processing subsystem (105) includes a plurality of modules. The plurality of modules includes an input metrics identification module (120), a computational module (125), an output metrics identification module (130) and an efficiency computation module (135).
[0055] The input metrics identification module (120) is configured to receive a plurality of inputs from a business organization. The plurality of inputs includes, but is not limited to, a store floor space, stock-keeping unit and number of promotional stalls. The computational module (125) is operatively coupled to the input metrics identification module (120) wherein the computational module (125) is configured to estimate a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers. The computational module (125) is configured to map the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area. Further, the computational module (125) is configured to compute a Serviceable Addressable Market value for each of the multiple stores using a geometrical computation to determine one or more operational factors. The output metrics identification module (130) is operatively coupled to the computational module (125) wherein the output metrics identification module (130) is configured to utilize a sales turnover and a number of acquired customers as outputs. The efficiency computation module (135) is operatively coupled to the output metrics identification module (130) and the input metric identification module wherein the efficiency computation module (135) is configured to estimate a relative efficiency score for each store using a Data Envelopment Analysis, the computed Serviceable Addressable Market value and the plurality of input parameters and output parameters wherein a score of one as the relative efficiency indicates optimal efficiency.
[0056] The bus (230) as used herein refers to be internal memory channels or computer network that is used to connect computer components and transfer data between them. The bus (230) includes a serial bus or a parallel bus, wherein the serial bus transmits data in bit-serial format and the parallel bus transmits data across multiple wires. The bus (230) as used herein, may include but not limited to, a system bus, an internal bus, an external bus, an expansion bus, a frontside bus, a backside bus and the like.
[0057] FIG. 5 illustrates a flow chart representing the steps involved in a method for evaluating efficiency of a multi-brand retail chain and determining benchmarks in accordance with an embodiment of the present disclosure. The method (300) includes receiving, by an input metrics identification module, a plurality of inputs from a business organization wherein the plurality of inputs includes a plurality of input parameters and a plurality of output parameters of the business in step (305). Examples of the plurality of input parameters includes, but is not limited to, a store floor space, stock-keeping unit and number of promotional stalls. Examples of the plurality of output parameters includes, but is not limited to, revenue per customer and total number of customers. The store floor space refers to the size of the store in terms of square footage. The Stock-Keeping Unit (SKU) refers to the number of unique products or items that the store carries. The number of promotional stalls refers to the number of areas in the store dedicated to promotions or special displays.
[0058] The method (300) includes estimating, by a computational module, a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers in step (310). The specific task here is to estimate the "catchment area" for each store in the retail chain. The catchment area refers to the geographical zone around a store from which it draws its customers. Essentially, it defines the area where the majority of the store's customers live or work. In other words, the catchment area is the area that provides the store with its customer base. The size and characteristics of this area can greatly influence the store's performance, as it reflects the pool of potential customers.
[0059] The method (300) includes mapping, by the computational module, the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area in step (315). A "map" is created that links the previously estimated catchment area with additional data. The data is processed and combined to produce a detailed analysis. Further, the catchment area (the geographical zone from which a store attracts its customers) and maps it against relevant census data. Census data typically includes demographic information such as population size, age distribution, income levels, and other social and economic indicators for specific geographical locations. The mapping process results in the creation of a Geographical Information System (GIS) for each store. The GIS is an estimate of the population that lives within the catchment area of each store.
[0060] The method (300) includes computing, by the computational module, a Serviceable Addressable Market (SAM) value for each of the multiple stores using a geometrical computation to determine one or more operational factors in step (320). The SAM value represents the portion of the total addressable market (the entire potential market for a product or service) that can realistically be served by each store. This value takes into account factors like the store's location, competition, and operational capacity. The SAM provides a more focused estimate of the market size that a store can actually target and serve effectively. The Serviceable Addressable Market is computed using Voronoi Tessellation.
[0061]
[0062] The method (300) includes utilizing, by an output metrics identification module, a sales turnover and a number of acquired customers as outputs in step (325). The sales turnover and the number of acquired customers is used to evaluate the performance of each store in the retail chain. Sales turnover measures the total revenue generated by the store, while the number of acquired customers indicates how many new customers the store has gained. These outputs are crucial for assessing the effectiveness and efficiency of the store's operations, providing essential data for further analysis and decision-making within the business organization.
[0063] The method (300) includes estimating, by an efficiency computation module, a relative efficiency score for each of the multiple stores using a Data Envelopment Analysis, the computed Serviceable Addressable Market value and the plurality of input parameters and output parameters, wherein the relative efficiency score of one indicates optimal efficiency wherein a score of one as the relative efficiency indicates optimal efficiency in step (330). The relative efficiency is a measure that compares each store's performance against other stores in the chain. It reflects how well a store uses its resources (like space, staff, and inventory) to generate outputs (like sales and customer acquisition).
[0064] DEA is a performance measurement technique that compares multiple entities (in this case, stores) to identify which ones are operating most efficiently. It assesses the efficiency of each store relative to the best-performing stores, taking into account the resources they use (inputs) and the outputs they produce (like sales or customer acquisition).
In one embodiment, the Serviceable Addressable Market is computed from a Total Addressable Market.
[0065] In one embodiment, efficiency of the multiple stores is predicted by an artificial intelligence model trained with a data set of store data. In such an embodiment, the relative efficiency for each store is compared and fed as a training data set to the artificial intelligence module. The AI model is trained on historical data from the stores, which might include sales figures, customer numbers, resource usage, and other relevant metrics. The AI model uses this data to learn patterns and relationships, enabling it to predict the efficiency of the stores based on new or existing data. By comparing these efficiency scores, the AI model learns how to identify factors that contribute to high or low efficiency, improving its predictive accuracy.
[0066] In another embodiment, the efficiency values of the multiple stores are compared. This comparison is used for benchmarking or identifying stores that need improvement.
[0067] A predictive model of a neural network is deployed to validate the Data Envelopment Analysis (DEA). Neural networks are particularly good at recognizing complex patterns in data. By deploying a neural network, the method can check whether the DEA results (which assess store efficiency) align with the predictions made by the AI. This validation process helps ensure that the DEA analysis is accurate and reliable.
[0068] Various embodiments of the present disclosure provides a system and method for evaluating efficiency of a multi-brand retail chain. The system (100) provides an integrated framework that includes economic model efficiency and computational geometry for evaluating efficiency and determining benchmarks for retail stores. The integrated framework applies to companies that are trying to compare the efficiency of retail stores and can be further extended with competitor information on product and promotions from market surveys. Specifically, the computational module (125) computes the SAM via Voronoi Tessellation and seamlessly combines DEA for efficiency evaluation of retail stores along with other inputs and outputs (such as floor space, SKUs, number of promotions, unique customers and revenue). This approach provides efficiency scores facilitating comparisons among multiple stores. Further, a neural network predictive model is used to validate the outcomes of DEA thereby fostering confidence to the business organization on the outcomes. The benchmarking is possible now based on efficiency values as computed at a holistic level with multiple inputs and outputs.
[0069] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.
[0070] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.
[0071] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, the order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. ,CLAIMS:1. A system (100) for evaluating efficiency of a multi-brand retail chain, comprising:
a processing subsystem (105) hosted on a server (110) and configured to execute on a network (115) to control communications among a plurality of modules, wherein the plurality of modules comprising:
characterized in that,
an input metrics identification module (120) configured to:
receive a plurality of inputs from a business organization wherein the plurality of inputs comprises a plurality of input parameters and a plurality of output parameters of a business;
a computational module (125) operatively coupled to the input metrics identification module (120), wherein the computational module (125) is configured to:
estimate a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers;
map the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area;
compute a Serviceable Addressable Market value for each of the multiple stores using a geometrical computation to determine one or more operational factors;
an output metrics identification module (130) operatively coupled to the input metrics identification module (120) wherein the output metrics identification module (130) is configured to utilize a sales turnover and a number of acquired customers as outputs; and
an efficiency computation module (135) operatively coupled to the output metrics identification module (130) and the input metrics identification module (120) wherein the efficiency computation module (135) is configured to estimate a relative efficiency score of each of the multiple stores using a Data Envelopment Analysis, the computed Serviceable Addressable Market value and the plurality of input parameters and output parameters, wherein the relative efficiency score of one indicates optimal efficiency.
2. The system (100) as claimed in claim 1, wherein the Serviceable Addressable Market is computed from a Total Addressable Market.

3. The system (100) as claimed in claim 1, wherein the Serviceable Addressable Market is computed using Voronoi Tessellation.

4. The system (100) as claimed in claim 1, comprising an artificial intelligence module (140) operatively coupled to the efficiency computation module (135) wherein the artificial intelligence module (140) is configured to predict efficiency of the multiple stores by an artificial intelligence model trained with a data set of store data.

5. The system (100) as claimed in claim 1, wherein the relative efficiency for each store is compared and fed as a training data set to the artificial intelligence module (140).

6. The system (100) as claimed in claim 1, comprising a benchmarking module (145) operatively coupled to the artificial intelligence module (140) wherein the benchmarking module (145) is configured to compare the multiple stores based on efficiency values.

7. The system (100) as claimed in claim 1, comprising an application module (150) operatively coupled to the benchmarking module (145) wherein the application module (150) is configured to utilize a plurality of technology stack.

8. The system (100) as claimed in claim 1, wherein a predictive model of a neural network is deployed to validate the accuracy of the Data Envelopment Analysis thereby ensuring reliability of the system (100) to the plurality of customers .

9. The system (100) as claimed in claim 1, comprising a database (155) to store past predictions of efficiencies pertaining to the plurality of stores.

10. A method (300) for evaluating efficiency of a multi-brand retail chain comprising:
receiving, by an input metrics identification module, a plurality of inputs from a business organization wherein the plurality of inputs comprises a plurality of input parameters and a plurality of output parameters; (305)
estimating, by a computational module, a catchment area of each of the multiple stores, wherein the catchment area defines a potential geographical zone from which the business organization attracts a plurality of customers; (310)
mapping, by the computational module, the catchment area with a corresponding census data pertaining to the geographical locations, wherein the mapping generates a Geographical Information System for each store to estimate a population residing in the said mapped catchment area; (315)
computing, by the computational module, a Serviceable Addressable Market value for each of the multiple stores using a geometrical computation to determine one or more operational factors; (320)
utilizing, by an output metrics identification module, a sales turnover and a number of acquired customers as outputs; (325) and
estimating, by an efficiency computation module, a relative efficiency score of each of the multiple stores using a Data Envelopment Analysis, the computed Serviceable Addressable Market and the plurality of input parameters and output parameters wherein the relative efficiency score of one indicates optimal efficiency. (330)
Dated this 02nd day of January 2025
Signature

Prakriti Bhattacharya
Patent Agent (IN/PA-5178)
Agent for the Applicant