FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION (See Section 10 and Rule 13)
Title of invention:
SYSTEM AND METHOD TO DYNAMICALLY MANAGE RETAIL
STORE REPLENISHMENT PARAMETERS
Applicant
Tata Consultancy Services Limited A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description
The following specification particularly describes the invention and the
manner in which it is to be performed.

TECHNICAL FIELD [001] The disclosure herein generally relates to a field of retail store replenishment management and, more particularly, to a system and method to dynamically manage retail store replenishment parameters.
BACKGROUND [002] In retail scenario, existing retail replenishment planning processes leverage a set of parameters such as replenishment frequency, order multiples, safety stock, etc. to arrive at a replenishment quantity requests from a facility like warehouse or stores. Typically, these parameters are configured only once, during initial deployment of the replenishment planning solution, and are based purely on expert experience. Predominantly, these rules remain static through the life of the planning solution and are updated only if special causes require it. Such parameters are also generalized for a broad range of products and the supply chain through which the product flows.
[003] Current systems lack capabilities to dynamically refine these parameters with due consideration on the implication of the change of one parameter on the other. This result in systems which are not agile and tend to get misaligned with the changing business context. Replenishment parameters heavily influence inventory performance which can impact sales and cash flow for a retailer.
[004] Further, the performance of existing retail replenishment planning processes is degraded because once the parameters are set during initial deployment, they undergo minimal change. Limited or non-existent periodic review of the parameters’ values and its performance. Although, changes in business context are known upfront, parameters are hardly aligned. No scientific mechanism available to identify a right parameter to change or trigger change. Identifying holistic impact of a single parameter value change is complex because of interplay of various parameters. It requires a periodic human intervention to align with

changing business context through off system analysis which may result in sub-optimal values. Typically, parameters are generalized and set at aggregated levels of product and location hierarchies for ease of management.
SUMMARY [005] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a processor-implemented method to dynamically manage retail store replenishment parameters is provided.
[006] The processor-implemented method includes receiving a plurality of information of one or more parameters pertaining to a retail replenishment planning of a facility. Herein, the plurality of information includes replenishment frequency, order multiples and safety stock. Further, the method includes analyzing the plurality of information to detect one or more scenarios using a pre-trained machine learning model and determining an influence of each of the one or more parameters on the detected one or more scenarios. It is to be noted that the one or more detected scenarios include a lack of enough inventory and a build-up of excess inventory.
[007] Further, the processor-implemented method includes predicting one or more values of each of the one or more parameters based on a predefined Key Performance Indicators (KPIs) of each of the one or more parameters and a combination of KPIs. Thus, the one or more parameters of the retail replenishment planning of the facility is optimized based on the predicted one or more values and a cost function of the facility.
[008] In another aspect, a system to dynamically manage retail store replenishment parameters is provided. The system includes at least one memory storing a plurality of instructions, and one or more hardware processors communicatively coupled with at least one memory, wherein one or more hardware

processors are configured to execute one or more modules. Further, the system includes a receiving module, an analyzing module, a determining module, a prediction module, and an optimization module. Herein, the receiving module is configured to receive a plurality of information of one or more parameters pertaining to a retail replenishment planning of a facility. Wherein, the plurality of information includes replenishment frequency, order multiples and safety stock.
[009] Furthermore, the analyzing module is configured to analyze the plurality of information to detect one or more scenarios using a pre-trained machine learning model. The determination module is configured to determine an influence of each of the one or more parameters on the detected one or more scenarios. The prediction module is configured to predict one or more values of each of the one or more parameters based on a predefined Key Performance Indicators (KPIs) of each of the one or more parameters and a combination of KPIs. Further, the optimization module of the system is configured to optimize the one or more parameters of the retail replenishment planning of the facility based on the predicted one or more values and a cost function of the facility.
[010] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
BRIEF DESCRIPTION OF THE DRAWINGS [011] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles.
[012] FIG. 1 illustrates an exemplary system to dynamically manage retail store replenishment parameters according to some embodiments of the present disclosure.

[013] FIG. 2 illustrates a schematic diagram of the system to dynamically manage retail store replenishment parameters in accordance with some embodiments of the present disclosure.
[014] FIG. 3 is a flow diagram illustrating a method to dynamically manage retail store replenishment parameters in accordance with some embodiments of the present disclosure.
DETAILED DESCRIPTION OF EMBODIMENTS [015] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope being indicated by the following claims.
[016] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[017] The embodiments herein provide a system and method to manage retail store replenishment parameters dynamically. Traditionally, the replenishment planning uses static rules and parameters which are updated periodically mostly through a human intervention without considering the holistic impact of the change. Herein, an automatic and intelligent detection of supply chain performance and change in the business environment can potentially lead to dynamic changes of

replenishment parameters. Further, an identification of relevant replenishment parameters and the range of values which can influence the supply chain performance. A dynamic parameter optimization provides a machine learning powered an automated parameter optimizing capability based on state, context, actual constraints and dynamic performance that adopts to changing business context to ensure an automated re-calibration of replenishment parameters at the appropriate time. The dynamic concurrent change of parameters considers an interplay within parameters at various levels with due consideration to an overall impact on the supply chain.
[018] Referring FIG. 1, illustrating a system (100) to dynamically manage retail store replenishment parameters. In the preferred embodiment, the system (100) comprises at least one memory (102) with a plurality of instructions, a plurality of user interface (104) and one or more hardware processors (106) which are communicatively coupled with the at least one memory (102) to execute modules therein.
[019] The hardware processor (106) may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the hardware processor (104) is configured to fetch and execute computer-readable instructions stored in the memory (102). Further, the system comprises a receiving module (108), an analyzing module (110), a determining module (112), a prediction module (114), and an optimization module (116).
[020] In the preferred embodiment of the disclosure, the receiving module (108) of the system (100) is configured to receive a plurality of information of one or more parameters pertaining to a retail replenishment planning of a facility. Herein, the plurality of information of one or more parameters includes replenishment frequency, order multiples and safety stock. The underling

consideration is of a value chain benefit which can be derived from the received plurality of information of one or more parameters.
[021] In the preferred embodiment of the disclosure, the analyzing module (110) of the system (100) is configured to analyze the plurality of information to detect one or more scenarios using a pre-trained machine learning model. Herein the pre-trained machine learning model is either a regression tree or a neural network. The one or more scenarios include a lack of enough inventory and a build¬up of excess inventory. The one or more scenarios depend upon variations in a business environment and corresponding infrastructure development. Usually, the business environment is based on predefined business rules applicable to a specific retailer.
[022] It would be appreciated that a pre-trained machine learning model is used to analyze recent transactional data in the supply chain pertaining to costs, inventory levels, and KPIs to extrapolate future KPIs based on recent data and demand forecast information for future time periods. Further, the pre-trained machine learning model is used to compute the likelihood of falling short of said KPIs due to frequent predicted stock-outs of certain products. This prediction could trigger re-computation of replenishment frequency of the identified products, with the new optimal value computed using a second machine learning algorithm such as reinforcement learning.
[023] In the preferred embodiment of the disclosure, the determining module (112) of the system (100) is configured to determine an influence of each of the one or more parameters on the detected one or more scenarios. Herein, the influence is computed as an expected value of KPIs, or as the probability of falling short of preferred values of KPIs. The expected value of KPIs is fulfilled using regression trees or a pre-trained artificial neural network, while the probability of falling short of preferred values of KPIs is fulfilled using a logistic regression or an artificial neural network.

[024] Herein, the computation of a revised parameter value is carried out using an artificial intelligence technique such as reinforcement learning. The pre-trained reinforcement learning is capable of predicting an impact of change of a certain parameter for a single product on the overall operation and KPIs of the supply chain. Thus, the pre-trained reinforcement learning is used to compute the revised value considering global effects.
[025] Referring FIG. 2, illustrating a schematic diagram, denotes three key functionalities of the system. In the first function, a decision is taken to revise one or more parameters for one or more products. The decision can be based on a set of triggers, including periodic, and driven by specific external events such as changes in supply chain operating characteristics. The same triggers may be automatically generated or manually generated. In the second function, the KPIs that are currently outside of acceptable ranges are identified. In the third function, a subset of potential parameter is identified from the set of tunable parameters, changes to potential parameter are computed, the impact of proposed changes on KPIs is estimated using a simulator, and the final values of changed parameters are computed to the supply chain for implementation.
[026] An illustration of the parameter value revision identification is provided in the table 1 and table 2, which lists the stocks of two products A and B over the course of 9 days. Product A is replenished every three days (Day 1,4,7) while product B is replenished every two days (Day 1,3,5,7,9) in the existing operations of the supply chain. However, Product A goes out-of-stock several times during the course of operations (on Day 3 and Day 6). The pre-trained machine learning model first identifies this problem as a statistically significant one, through an analysis of operating data. Second, it identifies the replenishment frequency of Product A as a potential parameter for update. It must also consider that Product B is replenished on Day 1,3,5,7,9, and the new parameters for Product A must not cause the capacity of the supply chain to be exceeded. Therefore, the model must change two parameters to achieve the desired results:

(i) change the replenishment frequency of Product A to two days
instead of three, and
(ii) give offset of one day to replenishment of Product A, so that it
operates in a staggered fashion compared to Product B.

Product Day 1 Day 2 Day 3 Day 4 Day 5 Day 6 Day 7 Day 8 Day 9
A 10 5 0 10 5 0 10 5 0
B 10 5 10 5 10 5 10 5 10
Table 1
The stock levels of both products are expected to demonstrate the following pattern after parameter change. Product A is now replenished on days 2,4,6,8.

Product Day 1 Day 2 Day 3 Day 4 Day 5 Day 6 Day 7 Day 8 Day 9
A 5 10 5 10 5 10 5 10 5
B 10 5 10 5 10 5 10 5 10
Table 2
[027] In the preferred embodiment, at least one of the one or more parameters is identified as a potential parameter for update by a pre-trained machine learning model that estimates the effect of the proposed change on KPIs of all other products and all other nodes in the supply chain. It would be appreciated that in the event of more than one parameter being able to affect the required change, the pre-trained machine learning model chooses the at least one potential parameter, the one that least affects other KPIs.
[028] In the preferred embodiment of the disclosure, the prediction module (114) of the system (100) is configured to predict one or more values of each of the one or more parameters based on a predefined Key Performance Indicators (KPIs) of each of the one or more parameters and a combination of KPIs.

[029] In the preferred embodiment of the disclosure, the optimization module (116) of the system (100) is configured to change the one or more parameters of the retail replenishment planning of the facility based on the predicted one or more values and a cost function of the facility.
[030] It would be appreciated that the dynamic parameter optimization provides a machine learning powered an automated parameter optimizing capability based on state, context, actual constraints and dynamic performance that adopts to changing business context to ensure an automated re-calibration of replenishment parameters at the appropriate time. The dynamic concurrent change of parameters considers an interplay within parameters at various levels with due consideration to an overall impact on the supply chain.
[031] Referring FIG. 3, a flow chart to illustrate a processor-implemented method (400) to dynamically manage retail store replenishment parameters. The method comprises one or more steps as follows.
[032] Initially, at the step (302), receiving a plurality of information of one or more parameters pertaining to a retail replenishment planning of a facility at a receiving module (108) of the system (100). The plurality of information includes replenishment frequency, order multiples and safety stock.
[033] In the preferred embodiment of the disclosure, at the next step (304), analyzing the received plurality of information at the analyzing module (110) of the system (100) to detect one or more scenarios using a pre-trained machine learning model. The one or more scenarios include a lack of enough inventory and a build¬up of excess inventory. Herein the pre-trained machine learning model is either a regression tree or a neural network. The one or more scenarios include a lack of enough inventory and a build-up of excess inventory. It is to be noted that the one or more scenarios depend upon variations in a business environment and corresponding infrastructure development.

[034] In the preferred embodiment of the disclosure, at the next step (306), determining an influence of each of the one or more parameters on the detected one or more scenarios using the determining module (112) of the system (100). Herein, the influence is computed as an expected value of KPIs, or as the probability of falling short of preferred values of KPIs. The expected value of KPIs is fulfilled using regression trees or a pre-trained artificial neural network, while the probability of falling short of preferred values of KPIs is fulfilled using a logistic regression or an artificial neural network.
[035] In the preferred embodiment of the disclosure, at the next step (308), predicting one or more values of each of the one or more parameters at the prediction module (114) of the system (100) based on a predefined Key Performance Indicators (KPIs) of each of the one or more parameters and a combination of KPIs.
[036] In the preferred embodiment of the disclosure, at the last step (310), optimizing, via one or more hardware processors, the one or more parameters of the retail replenishment planning of the facility at the optimization module (116) of the system (100) based on the predicted one or more values and a cost function of the facility. Herein, dynamic parameter optimization provides a machine learning powered an automated parameter optimizing capability based on state, context, actual constraints and dynamic performance that adopts to changing business context to ensure an automated re-calibration of replenishment parameters at the appropriate time. The dynamic concurrent change of parameters considers an interplay within parameters at various levels with due consideration to an overall impact on the supply chain.
[037] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do

not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[038] The embodiments of present disclosure herein address unresolved problem in existing retail replenishment planning processes which are leveraging a set of parameters such as replenishment frequency, order multiples, safety stock, etc. to arrive at a replenishment quantity requests from a facility like warehouse or stores. Typically, these parameters are configured only once, during initial deployment of the replenishment planning solution, and are based purely on expert experience. Predominantly, these rules remain static through the life of the planning solution and are updated only if special causes require it. Such parameters are also generalized for a broad range of products and the supply chain through which the product flows. Current systems lack capabilities to dynamically refine these parameters with due consideration on the implication of the change of one parameter on the other. This result in systems which are not agile and tend to get misaligned with the changing business context. Replenishment parameters heavily influence inventory performance which can impact sales and cash flow for a retailer.
[039] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware

means, and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
[040] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[041] The illustrated steps are set out to explain the exemplary
embodiments shown, and it should be anticipated that ongoing technological
development will change the manner in which particular functions are performed.
These examples are presented herein for purposes of illustration, and not limitation.
Further, the boundaries of the functional building blocks have been arbitrarily
defined herein for the convenience of the description. Alternative boundaries can
be defined so long as the specified functions and relationships thereof are
appropriately performed. Alternatives (including equivalents, extensions,
variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.

[042] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[043] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.

We Claim:
1. The system comprising:
at least one memory storing a plurality of instructions;
one or more hardware processors communicatively coupled with at least one memory, wherein one or more hardware processors are configured to execute one or more modules;
a receiving module configured to receive a plurality of information of one or more parameters pertaining to a retail replenishment planning of a facility, wherein the plurality of information includes replenishment frequency, order multiples and safety stock;
an analyzing module configured to analyze the plurality of information to detect one or more scenarios using a pre-trained machine learning model, wherein one or more scenarios include a lack of predefined inventory and a build-up of predefined inventory;
a determining module configured to determine influence of each of the one or more parameters on the detected one or more scenarios, wherein the influence of each of the one or more parameters is determined as an expected value of KPIs, or as probability of falling short of preferred values of KPIs;
a prediction module configured to predict one or more values of each of the one or more parameters based on predefined Key Performance Indicators (KPIs) of each of the one or more parameters and a combination of KPIs; and
an optimization module configured to optimize the one or more parameters of the retail replenishment planning of the facility based on the predicted one or more values and the combination of KPIs.
2. The system claimed in claim 1, wherein a change in performance of the one
or more parameters depend on change in the performance of supply chain
and a change in the business environment.

3. The system claimed in claim 1, wherein a long-term effect of change is identified in one or more parameters on the performance of all other products and nodes in the supply chain.
4. The system claimed in claim 1, wherein triggering at least one parameter is based on the one or more criteria, wherein the one or more criteria include time elapsed since last update, change in operating KPIs of the supply chain, forecasted change in demand or supply patterns in the supply chain.
5. The system claimed in claim 1, wherein triggering of at least one parameter update is possible based on a user intervention.
6. The system claimed in claim 1, wherein the expected value of KPIs is fulfilled using regression trees, and the probability of falling short of preferred values of KPIs is fulfilled using a logistic regression.
7. A processor-implemented method to comprising:
receiving, via one or more hardware processors, a plurality of information of one or more parameters pertaining to a retail replenishment planning of a facility, wherein the plurality of information includes replenishment frequency, order multiples and safety stock;
analyzing, via one or more hardware processors, the received plurality of information to detect one or more scenarios using a pre-trained machine learning model, wherein one or more scenarios include a lack of predefined inventory and a build-up of predefined inventory;
determining, via one or more hardware processors, an influence of each of the one or more parameters on the detected one or more scenarios, wherein the influence of each of the one or more parameters is determined as an expected value of KPIs, or as probability of falling short of preferred values of KPIs;

predicting, via one or more hardware processors, one or more values of each of the one or more parameters based on predefined Key Performance Indicators (KPIs) of each of the one or more parameters and a combination of KPIs; and
optimizing, via one or more hardware processors, the one or more parameters of the retail replenishment planning of the facility based on the predicted one or more values and the combination of KPIs.
8. The method claimed in claim 7, wherein a change in performance of the one or more parameters depend on change in the performance of supply chain and a change in the business environment.
9. The method claimed in claim 7, wherein a long-term effect of change is identified in one or more parameters on the performance of all other products and nodes in the supply chain.
10. The method claimed in claim 7, wherein triggering at least one parameter is based on the one or more criteria, wherein the one or more criteria include time elapsed since last update, change in operating KPIs of the supply chain, forecasted change in demand and supply patterns in the supply chain.
11. The method claimed in claim 7, wherein triggering of at least one parameter update is possible based on a user intervention.
12. The method claimed in claim 7, wherein the influence is determined as an expected value of KPIs, or as probability of falling short of preferred values of KPIs, wherein the expected value of KPIs is fulfilled using regression trees, and the probability of falling short of preferred values of KPIs is fulfilled using a logistic regression.