Description:FIELD OF THE INVENTION

[0001] The present invention relates to an AI-powered customer segmentation system for retail optimization that is capable of improving customer segmentation accuracy by analyzing and identifying the root causes of customer behavior, thus enabling more targeted marketing strategies that address specific needs and preferences.

BACKGROUND OF THE INVENTION

[0002] Customer segmentation is essential for retail optimization as the customer segmentation enables businesses to understand and target distinct groups of customers based on their behaviors, preferences, and purchasing patterns. By dividing a diverse customer base into meaningful segments, retailers personalize marketing efforts, optimize product offerings, and tailor shopping experiences, resulting in improved customer satisfaction and loyalty. The customer segmentation also allows for more efficient use of resources, such as inventory management, pricing strategies, and promotional campaigns, ensuring better return on investment. Ultimately, effective customer segmentation leads to effective decision-making, increased sales, and a competitive edge in the marketplace.

[0003] Traditional methods of customer segmentation in retail optimization often rely on basic demographics like age, gender, income, and location. These methods group customers into broad categories, which helps retailers tailor their offerings, but lacks precision. Though useful, they don’t capture deeper behavioral insights such as purchase patterns, preferences, or loyalty. As a result, these methods are less effective in personalizing experiences and maximizing profitability compared to other modern techniques. The drawback of traditional segmentation methods is that they oversimplify customer groups, focusing only on demographics and ignoring more nuanced factors like buying behavior, preferences, and customer lifetime value. This approach leads to generic marketing, missed opportunities for personalization, and less effective resource allocation. Retailers fail to fully understand customer needs, which hinders targeted strategies and reduces overall profitability.

[0004] US20080082386A1 discloses systems and methods are disclosed for managing customers using customer segmentation. In one embodiment, a customer relationship manager may implement a customer management architecture to define one or more customer segmentation rules based on one or more business metrics, and to organize customers into one or more customer groups based on the one or more customer segmentation rules. The customer relationship manager may then establish a customer segment based on the one or more customer groups, and develop a segment management plan for managing customers in the customer segment. Using the customer management architecture, the customer relationship manager may further set a growth target for the customer segment, and track performance of the customer segment in achieving the growth target.

[0005] US20220335460A1 discloses systems and methods for optimizing pricing of products within a retailer are provided. Such systems and methods include determining a set of products to be included in an elasticity computation. Next, the number of days to collect transaction logs for a given product is determined, responsive to sales volumes for each given product. These transaction logs are then collected and used to compute the elasticities for these products. Products that were not included for calculation of elasticities have elasticities imputed for them. A set of constraints are received. Optimal prices are then generated based upon the objectives, rules and price elasticities.

[0006] Conventionally, many systems have been developed for customer segmentation for retail optimization, but these existing systems lack in adapting customer segment definitions and interventions based on real-time sales data, seasonal trends, and feedback loops for ensuring timely and relevant customer engagement. In addition, these systems fail in enhancing customer understanding by failing to analyze sentiment and emotional readiness for allowing retailers to tailor outreach campaigns and product recommendations according to customer moods and preferences.

[0007] In order to overcome the aforementioned drawbacks, there exists a need in the art to develop a system that requires to be capable of adapting customer segment definitions and interventions based on real-time sales data, seasonal trends, and feedback loops for ensuring timely and relevant customer engagement. Additionally, the developed system needs to be capable of enhancing customer understanding by analyzing sentiment and emotional readiness for allowing retailers to tailor outreach campaigns and product recommendations according to customer moods and preferences.

OBJECTS OF THE INVENTION

[0008] The principal object of the present invention is to overcome the disadvantages of the prior art.

[0009] An object of the present invention is to develop a system that is capable of improving customer segmentation accuracy by analyzing and identifying the root causes of customer behavior, thus enabling more targeted marketing strategies that address specific needs and preferences.

[0010] Another object of the present invention is to develop a system that is capable of dynamically adapting customer segment definitions and interventions based on real-time sales data, seasonal trends, and feedback loops, thus ensuring timely and relevant customer engagement.

[0011] Yet another object of the present invention is to develop a system that is capable of enhancing customer understanding by analyzing sentiment and emotional readiness, thus allowing retailers to tailor outreach campaigns and product recommendations according to customer moods and preferences.

[0012] The foregoing and other objects, features, and advantages of the present invention will become readily apparent upon further review of the following detailed description of the preferred embodiment as illustrated in the accompanying drawings.

SUMMARY OF THE INVENTION

[0013] The present invention relates to an AI-powered customer segmentation system for retail optimization that is capable of dynamically adapting customer segment definitions and interventions based on real-time sales data, seasonal trends, and feedback loops, thus ensuring timely and relevant customer engagement.

[0014] According to an aspect of the present invention, a AI-powered customer segmentation system for retail optimization comprises of a causal inference-based segmentation (CIBS) module that employs causal graphs and counterfactual analysis to identify the cause of customer churn, loyalty, or high spending that enable the generation of actionable marketing strategies based on the root causes of client behavioral spending, an explainable segment justification engine (X-SJE) employing regressive machine learning (ML) protocols with AI models to generate human-readable reasons behind customer segment assignments and predicted behaviors that provide visual dashboards for marketing teams to understand reasons for the customer’s loyalty, customer switching between brands and also generate suggestions to prevent customer switch, a reinforcement learning (RL) model for real-time adaptive segment shifting configured to dynamically adjust customer segment definitions and interventions based on live sales data, feedback loops, and seasonal trends that helps predict customer migration across segments and suggest pre-emptive strategies, the reinforcement learning (RL) model for real-time adaptive segment shifting is coupled to a sentiment-aware purchase intent mapping (SAPIM) module, the SAPIM module combines natural language processing (NLP)-based sentiment analysis of reviews/social posts of customers, the NLP-based sentiment analysis combined with product preference trends on social media helps identify mood-weighted customer segments that enable retailers to develop outreach campaigns based on the real-time emotional readiness of the customer, the NLP-based sentiment analysis enables generation of emotionally tuned recommendations (ETR) that matches segment recommendations with emotional tone, brand perception, and trust level of individual customers and also offers adaptive messaging tones in campaigns generated by retail outlets, a cross-platform micro-segmentation (CPMS) module employs graph-based AI models to segment micro-communities and enables visual analytics that helps to track customer behavior across web, mobile, in-store purchases, and IoT touchpoints.

[0015] While the invention has been described and shown with particular reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0016] These and other features, aspects, and advantages of the present invention will become better understood with regard to the following description, appended claims, and accompanying drawings where:
Figure 1 illustrates a block diagram of an AI-powered customer segmentation system for retail optimization.

DETAILED DESCRIPTION OF THE INVENTION

[0017] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.

[0018] In any embodiment described herein, the open-ended terms "comprising," "comprises,” and the like (which are synonymous with "including," "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of," consists essentially of," and the like or the respective closed phrases "consisting of," "consists of, the like.

[0019] As used herein, the singular forms “a,” “an,” and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.

[0020] The present invention relates to an AI-powered customer segmentation system for retail optimization that is capable of enhancing customer understanding by analyzing sentiment and emotional readiness, thus allowing retailers to tailor outreach campaigns and product recommendations according to customer moods and preferences.

[0021] Referring to Figure 1, a block diagram of an AI-powered customer segmentation system for retail optimization is illustrated, comprising a causal inference-based segmentation (CIBS) module, an explainable segment justification engine (X-SJE), a reinforcement learning (RL) model, a sentiment-aware purchase intent mapping (SAPIM) module and a cross-platform micro-segmentation (CPMS) module and a processor.

[0022] The system disclosed herein comprises of a causal inference-based segmentation (CIBS) module. The CIBS module employs causal graphs and counterfactual analysis to identify the cause of customer churn, loyalty, or high spending that enables the generation of actionable marketing strategies based on the root causes of client behavioral spending. The Causal Inference-Based Segmentation (CIBS) module operates by leveraging causal graphs and counterfactual reasoning to derive meaningful insights into customer behavior. The process begins by collecting and preparing comprehensive customer data, which includes demographic details, transactional histories, interactions with the brand, and external factors. The CIBS module generates causal graphs that visually represent the relationships between different variables, such as marketing efforts, customer service interactions, product usage patterns, and external influences and their potential causal impact on customer behavior. This module allows the system to hypothesize and examine direct and indirect cause-effect relationships among different factors influencing customer actions.

[0023] The CIBS module employs counterfactual analysis to estimate what happens if certain interventions or factors are different. For instance, it might assess how a customer behaves if they are exposed to a different marketing campaign or product recommendation. By simulating these what-if scenarios, the module identifies critical causal factors that lead to specific outcomes like churn or high spending. The module uses machine learning protocols and statistical methods such as Bayesian networks to quantify these causal effects and separate correlation from causation. This step provides a robust understanding of which factors truly drive customer behavior rather than just being associated with them.

[0024] Finally, the insights derived from the causal analysis are applied to segment the customer base into distinct groups, each with tailored actionable strategies. For instance, the system identifies a segment of customers whose loyalty is driven by personalized customer service interactions or a group whose spending is significantly impacted by targeted promotions. Based on these causal relationships, the system recommends specific interventions such as personalized marketing campaigns, product bundling, or customer retention programs aimed at addressing the root causes of the behaviors. This segmentation process helps businesses optimize their marketing efforts by providing a clear roadmap for interventions that will have the greatest impact on customer outcomes.

[0025] The CIBS module is coupled to an explainable segment justification engine (X-SJE). The X-SJE employs regressive machine learning (ML) protocols with AI models to generate human-readable reasons behind customer segment assignments and predicted behaviors that provide visual dashboards for marketing teams to understand reasons for the customer’s loyalty, customer switching between brands and also generate suggestions to prevent customer switch. The Explainable Segment Justification Engine (X-SJE) works by providing transparency and interpretability to the customer segment assignments and their predicted behaviors. Once the CIBS module identifies customer segments based on causal factors, the X-SJE takes over by applying the regressive machine learning protocols to analyze and justify the assignments. The X-SJE begins by using machine learning models, such as decision trees, to examine the causal relationships between the identified segments and their corresponding behavioral patterns. The goal of this step is to produce human-readable explanations for why specific customers are classified into particular segments, such as why a customer is likely to exhibit high spending or is at risk of churn.

[0026] The key strength of the X-SJE lies in the ability to make machine learning results interpretable for human stakeholders, particularly marketing teams. As the system generates segment assignments, it employs explainability techniques like Shapley values to break down the decision-making process of the AI models into understandable chunks. For example, if a customer is predicted to switch brands, the X-SJE might explain that this behavior is largely driven by recent negative feedback on customer service interactions or the lack of targeted offers. By outputting this reasoning in simple, understandable terms, it ensures that marketing teams are equipped with clear, actionable insights into the root causes of customer behaviors like loyalty or switching, which otherwise be opaque in black-box AI models.

[0027] The X-SJE not only explains why customers behave in certain ways but also offers predictive insights into what actions businesses take to mitigate undesirable behaviors like churn or brand switching. By analyzing historical customer behavior data and the causal factors involved, the engine suggests targeted interventions that align with the specific drivers of customer dissatisfaction or loyalty. For example, if the model identifies that a lack of personalized communication is contributing to customer churn, the X-SJE recommends implementing a personalized loyalty program or improving customer touchpoints to retain the customer base. The system compiles these suggestions into a visual dashboard, providing marketing teams with a clear, actionable roadmap of how to address specific customer needs and preferences to reduce churn and increase brand loyalty.

[0028] The explainable segment justification engine (X-SJE) is coupled to a reinforcement learning (RL) model for real-time adaptive segment shifting. The RL models are configured to dynamically adjust customer segment definitions and interventions based on live sales data, feedback loops, and seasonal trends that helps predict customer migration across segments and suggest pre-emptive strategies. The Reinforcement Learning (RL) model plays a crucial role in dynamically adapting and fine-tuning customer segment definitions and intervention strategies in real-time. The RL model works by continuously interacting with the evolving sales data, feedback loops, and seasonal trends to optimize marketing strategies. The Reinforcement Learning (RL) model operates on the principle of a feedback loop, where it takes actions based on the current customer segment state, observes the outcomes (rewards or penalties), and adjusts its strategies accordingly. The input to the RL model includes live customer behavior data, sales performance, customer feedback, and external factors such as seasonal trends or market shifts, which influence the model's decision-making process.

[0029] The RL model is structured around an agent-environment framework. The agent in this case is the RL model, which aims to maximize long-term rewards by making decisions about how to adjust customer segments and marketing interventions. The environment consists of the customer data, segment definitions, and the external factors influencing customer behavior. The model defines actions such as adjusting marketing campaigns, shifting customer segments, offering personalized promotions, or changing the timing of customer interactions. Each action has an associated reward or penalty, based on the observed customer responses, whether they lead to higher loyalty, reduced churn, or increased spending. Over time, the RL model learns which interventions lead to the best outcomes, refining the strategy to respond to changes in real-time customer behavior.

[0030] The RL model continuously monitors customer migration patterns across segments, which is influenced by changes in customer preferences, external market conditions, or promotional activities. As customers move between segments, the RL model predicts these transitions and proactively suggests pre-emptive strategies to mitigate negative outcomes, such as offering targeted retention offers or modifying customer engagement tactics. The RL model uses dynamic segmentation to ensure that customer groups are not static but evolve with changing behavior patterns. The model also incorporates seasonal trends and feedback loops, learning to adjust the strategies based on time-sensitive factors such as holiday seasons, product launches, or price changes. By continuously optimizing customer segment assignments and interventions, the RL model ensures that businesses maintain an adaptive, data-driven marketing approach that is always aligned with real-time customer behavior and market conditions.

[0031] The reinforcement learning (RL) model for real-time adaptive segment shifting is coupled to a sentiment-aware purchase intent mapping (SAPIM) module. The SAPIM module combines natural language processing (NLP)-based sentiment analysis of reviews/social posts of customers. The NLP-based sentiment analysis combined with product preference trends on social media helps to identify mood-weighted customer segments that enable retailers to develop outreach campaigns based on the real-time emotional readiness of the customer.

[0032] The Sentiment-Aware Purchase Intent Mapping (SAPIM) module integrates sentiment analysis and product preference trends to gauge the emotional state and readiness of customers to make a purchase. The Sentiment-Aware Purchase Intent Mapping (SAPIM) module leverages Natural Language Processing (NLP) to analyze customer-generated content, such as reviews, social media posts, and online interactions. In addition to sentiment, the module analyzes customer discussions around specific products or services to capture preference trends. This helps SAPIM identify which products customers are actively interested in or excited about, and how their sentiment fluctuates over time. By combining these insights, the module maps customer emotional states with their likelihood to make a purchase, allowing the system to categorize customers into mood-weighted segments.

[0033] Once the mood-weighted segments are established, SAPIM uses these insights to dynamically inform the Reinforcement Learning (RL) model for adaptive segment shifting. For instance, customers exhibiting high positive sentiment and excitement for a product identified as ready-to-purchase and targeted with personalized offers or timely promotions. Conversely, customers expressing frustration or dissatisfaction are flagged as high churn risk and prioritized for retention strategies, such as customer service outreach or exclusive offers. The sentiment-based customer mapping allows businesses to adjust their marketing and outreach strategies based on real-time emotional readiness, helping to ensure that campaigns are not only aligned with customer interests but also emotionally resonant with their current state. By integrating sentiment analysis with customer purchase intent, SAPIM optimizes timing and relevance, increasing the effectiveness of marketing campaigns while enhancing customer engagement.

[0034] The NLP-based sentiment analysis enables generation of emotionally tuned recommendations (ETR) that matches segment recommendations with emotional tone, brand perception, and trust level of individual customers and also offers adaptive messaging tones in campaigns generated by retail outlets. The Emotionally Tuned Recommendations (ETR) generated by the NLP-based sentiment analysis are designed to align customer segmentation with emotional tones, brand perception, and trust levels. As sentiment analysis processes customer reviews, social media posts, and interactions, it not only identifies the emotional sentiment behind the content but also evaluates the trust and perception customers have toward the brand. For instance, a customer expressing positive sentiment and high trust receives recommendations that reinforce brand loyalty and deepen engagement, such as exclusive offers or loyalty rewards. Conversely, a customer with negative sentiment or low trust receives more carefully crafted messages aimed at rebuilding that trust, such as apologetic tones, personalized solutions, or product recommendations that address previous dissatisfaction. This personalized approach ensures that the emotional context of each customer’s experience is taken into account when making product suggestions, leading to more meaningful and impactful interactions.

[0035] By incorporating adaptive messaging tones in campaign strategies, the system tailors the communications to fit the customer's emotional state. For example, if a customer expresses frustration on social media about a delayed product delivery, the recommendation engine will adapt its tone to a more empathetic, solution-focused approach, offering apologies or potential solutions rather than generic promotional content. On the other hand, customers showing excitement or positive sentiment toward a product might receive more enthusiastic, energetic messaging, encouraging immediate purchase with time-limited offers or reminders of the product's benefits. This adaptive messaging approach ensures that marketing campaigns are not just relevant in terms of product suggestions but also resonate emotionally, improving customer engagement and the likelihood of successful conversion. Through emotionally attuned recommendations, retailers create a more personalized and emotionally intelligent customer experience, enhancing brand perception and customer satisfaction.

[0036] The sentiment-aware purchase intent mapping (SAPIM) module is coupled to a cross-platform micro-segmentation (CPMS) module. The CPMS module employs graph-based AI models to segment micro-communities and enables visual analytics that helps to track customer behavior across web, mobile, in-store purchases, and IoT touchpoints. The Cross-Platform Micro-Segmentation (CPMS) module operates by using graph-based AI models to map and segment micro-communities of customers across various touchpoints such as web, mobile apps, in-store interactions, and IoT-enabled systems. The first step in the CPMS process is to collect multi-channel customer behavior data. This includes browsing patterns from websites, transaction histories from mobile apps or in-store purchases, and data from connected systems. The module then constructs a customer behavior graph where nodes represent individual customers, and edges denote interactions, behaviors, or shared attributes between them. These graphs help visualize the relationships between customers and their cross-platform activities, forming the basis for segmenting customers into micro-communities based on shared behaviors and preferences.

[0037] The graph-based models used in CPMS are highly dynamic and evolve over time. They leverage techniques such as community detection protocols and graph convolutional networks (GCNs) to identify clusters or sub-groups within the customer base. These clusters represent different micro-segments that exhibit similar behaviors or preferences across multiple platforms. For instance, a micro-community is a plurality of customers who frequently browses a specific category of products on the website, tends to purchase them via user-interface, and also shows interest in in-store promotions related to those products. The system then groups these customers into a distinct micro-segment, allowing for hyper-targeted marketing strategies. The use of graph-based AI enables the module to capture complex, non-linear relationships between behaviors across different touchpoints, ensuring a more accurate segmentation than traditional methods.

[0038] Additionally, the visual analytics capabilities of the CPMS module provide actionable insights to marketing teams by presenting customer behavior trends and micro-segment distributions through interactive dashboards. These dashboards allow teams to track customer interactions across multiple channels in real time and identify emerging behaviors or shifts in preferences. For example, the system identifies that a specific micro-community is increasingly engaging with IoT-enabled product features, such as voice-enabled purchasing, or is responding to location-based promotions when in proximity to stores. By analyzing these behaviors, the module recommends targeted actions, such as personalized messaging, loyalty incentives, or cross-platform promotions that align with specific customer needs. This comprehensive, cross-channel view of customer behavior helps businesses make more informed decisions on resource allocation and campaign optimization, ensuring that marketing efforts are more effective and customer-centric.

[0039] The modules and engine are embedded in a memory to be executed by a processor. The modules and engine are embedded within the memory architecture to be executed by the processor. This means that all the computational tasks related to customer data processing, behavioral analysis, segmentation, and campaign optimization are stored in the system’s memory and run on the processor that handles the execution of protocols and models. The processor interprets the input data, processes it according to the predefined models and learning protocols, and outputs actionable insights and recommendations. This integration enables the seamless operation of the entire system, facilitating real-time analytics, adaptive interventions, and dynamic segmentation across multiple customer touchpoints. The memory and processor together ensure that the system handles large volumes of data efficiently, enabling continuous learning and optimization of customer engagement strategies.

[0040] The present invention works best in the following manner, where the causal inference-based segmentation (CIBS) module is disclosed that employs causal graphs and counterfactual analysis to identify the cause of customer churn, loyalty, or high spending that enable the generation of actionable marketing strategies based on the root causes of client behavioral spending. The CIBS module is coupled to the explainable segment justification engine (X-SJE). The X-SJE employs regressive machine learning (ML) protocols with AI models to generate human-readable reasons behind customer segment assignments and predicted behaviors that provide visual dashboards for marketing teams to understand reasons for the customer’s loyalty, customer switching between brands and also generate suggestions to prevent customer switch. The explainable segment justification engine (X-SJE) is coupled to the reinforcement learning (RL) model for real-time adaptive segment shifting.

[0041] In continuation, the RL models are configured to dynamically adjust customer segment definitions and interventions based on live sales data, feedback loops, and seasonal trends that helps predict customer migration across segments and suggest pre-emptive strategies. The reinforcement learning (RL) model for real-time adaptive segment shifting is coupled to the sentiment-aware purchase intent mapping (SAPIM) module. The SAPIM module combines natural language processing (NLP)-based sentiment analysis of reviews/social posts of customers. The NLP-based sentiment analysis combined with product preference trends on social media helps identify mood-weighted customer segments that enable retailers to develop outreach campaigns based on the real-time emotional readiness of the customer. The NLP-based sentiment analysis enables generation of emotionally tuned recommendations (ETR) that matches segment recommendations with emotional tone, brand perception, and trust level of individual customers and also offers adaptive messaging tones in campaigns generated by retail outlets. The sentiment-aware purchase intent mapping (SAPIM) module is coupled to the cross-platform micro-segmentation (CPMS) module. The CPMS module employs graph-based AI models to segment micro-communities and enables visual analytics that helps tracks customer behavior across web, mobile, in-store purchases, and IoT touchpoints.

[0042] Although the field of the invention has been described herein with limited reference to specific embodiments, this description is not meant to be construed in a limiting sense. Various modifications of the disclosed embodiments, as well as alternate embodiments of the invention, will become apparent to persons skilled in the art upon reference to the description of the invention. , C , C , C , Claims:1. A AI-powered customer segmentation system for retail optimization, the system comprising:

a. A causal inference-based segmentation (CIBS) module; coupled to

b. An explainable segment justification engine (X-SJE); coupled to

c. A reinforcement learning (RL) model for real-time adaptive segment shifting; coupled to

d. A sentiment-aware purchase intent mapping (SAPIM) module; coupled to

e. A cross-platform micro-segmentation (CPMS) module;

Wherein the modules and engine are embedded in a memory to be executed by a processor.

2. The AI-powered customer segmentation system for retail optimization as claimed in claim 1, wherein the CIBS module employs causal graphs and counterfactual analysis to identify the cause of customer churn, loyalty, or high spending that enable generation of actionable marketing strategies based on root causes of client behavioral spending.

3. The AI-powered customer segmentation system for retail optimization as claimed in claim 1, wherein the X-SJE employs regressive machine learning (ML) protocols with AI models to generate human-readable reasons behind customer segment assignments and predicted behaviors that provides visual dashboards for marketing teams to understand reasons for customer’s loyalty, customer switching between brands and also generate suggestions to prevent customer switch.

4. The AI-powered customer segmentation system for retail optimization as claimed in claim 1, wherein the RL models are configured to dynamically adjust customer segment definitions and interventions based on live sales data, feedback loops, and seasonal trends that helps predict customer migration across segments and suggest pre-emptive strategies.

5. The AI-powered customer segmentation system for retail optimization as claimed in claim 1, wherein the SAPIM module combines natural language processing (NLP)-based sentiment analysis of reviews/social posts of customers.

6. The AI-powered customer segmentation system for retail optimization as claimed in claim 5, wherein the NLP-based sentiment analysis combined with product preference trends on the social media helps identify mood-weighted customer segments that enables retailers to develop outreach campaigns based on real-time emotional readiness of the customer.

7. The AI-powered customer segmentation system for retail optimization as claimed in claim 1, wherein the CPMS module employs graph-based AI models to segment micro-communities and enables visual analytics that helps tracks customer behavior across web, mobile, in-store purchases, and IoT touchpoints.

8. The AI-powered customer segmentation system for retail optimization as claimed in claim 6, wherein the NLP-based sentiment analysis enables generation of emotionally tuned recommendations (ETR) that matches segment recommendations with emotional tone, brand perception, and trust level of individual customers and also offers adaptive messaging tones in campaigns generated by retail outlets.