Predictive Analytics for Enhanced Fashion Sales at Benetton India

Atul A. Behera, Post Graduate Academic Scholar, Department of Fashion Management Studies, National Institute of Fashion Technology, Ministry of Textiles, Govt of India, Daman Campus.

Dr. Rahul Kushwaha, Assistant Professor, Department of Fashion Management Studies, National Institute of Fashion Technology, Ministry of Textiles, Govt of India, Daman Campus.

Abstract

This study explores the sales performance of menswear categories at United Colors of Benetton, focusing on sell-through rates, average selling prices, and discounting strategies across Spring-Summer (23A, 24A) and Autumn-Winter (AW) seasons. Using secondary sales data, the research identifies top-performing categories such as Jackets and Woven Tops, highlights pricing challenges in Denim and Accessories, and reveals sharp disparities in store performance. A quantitative approach with descriptive and comparative analysis informs strategic buying recommendations for AW25. The study proposes reallocation of inventory, pricing corrections, and focused assortment planning to improve profitability and minimize dead stock. The findings aim to assist retail planners in aligning future buys with actual consumer demand patterns.

Keywords

Menswear Sales Performance, Sell-Through Rate (STR), Average Selling Price (ASP), Inventory Reallocation, Assortment Planning, Predictive Retail Analytics

Introduction

This report presents a comprehensive data-driven analysis of the menswear category at United Colors of Benetton, with the objective of optimizing assortment planning, enhancing sell-through rates, and improving overall inventory efficiency. By leveraging historical sell-through data from previous seasons—specifically Spring-Summer 2023 (23A) and Spring-Summer 2024 (24A)—the study evaluates performance across key categories such as Jackets, Denim, Knit Bottoms, Woven Tops, and more. The analysis encompasses pricing dynamics (Average Selling Price trends), discounting strategies, store-level performance, and MRP-wise product effectiveness to determine strategic buying depth, product development focus, and margin optimization opportunities. In a highly competitive and seasonal fashion retail environment, the ability to forecast demand accurately and align buying decisions with real-time market signals is critical. This study identifies both high-performing and underperforming categories and price bands, offering actionable insights to reduce dead stock, maximize full-price sell-through, and allocate inventory more effectively across diverse store formats, including high-traffic airport locations and emerging Tier 2 cities. The findings aim to support smarter merchandising strategies for the upcoming Autumn-Winter 2025 season, ensuring a leaner, more profitable product mix aligned with consumer expectations.

Literature Review

Kwon, W. S., Ha-Brookshire, J. E., & Norum, P. (2020). Predictive analytics for assortment planning in fashion retailing. Journal of Retailing and Consumer Services, 53, 101962.This study examines how predictive analytics enhances assortment planning by using historical sales and product attributes. The authors emphasize data-driven decision-making in optimizing inventory and meeting customer preferences. The framework is relevant to fashion retail contexts where accurate forecasting can significantly influence profitability.

Fisher, M. L., Gallino, S., & Li, J. (2017). Competition-based dynamic pricing in online retailing: A methodology validated with field experiments. Management Science, 64(6), 2496–2514.The authors explore dynamic pricing based on competitive factors and validate their model with real retail data. Their insights are valuable for fashion retailers managing multiple price bands and trying to maintain margin integrity while responding to fluctuating demand.

Chen, W., Murray, R., & Van Wassenhove, L. N. (2013). Assortment planning for retailers using store-level transaction data. Operations Research, 61(5), 1030–1047. This paper presents a store-specific assortment planning model using transactional data. It supports tailoring product mixes at the store level, aligning directly with strategies used to manage STR differences between top-performing and underperforming locations.

Cachon, G. P., & Swinney, R. (2011). The value of fast fashion: Quick response, enhanced design, and strategic consumer behavior. Management Science, 57(4), 778–795.Cachon and Swinney highlight how fast fashion companies use speed and responsive design to meet demand. Their findings are important for understanding the balance between rapid inventory turnover and product development in seasonal retail.

Lee, H. L., & Tang, C. S. (2017). Socially and environmentally responsible value chain innovations: New operations management research opportunities. Management Science, 63(3), 721–734.This article investigates sustainability in value chains and emphasizes how efficient inventory planning can reduce waste. The findings are relevant to fashion retail, where markdowns and dead stock contribute to environmental and financial inefficiency.

Elmaghraby, W., &Keskinocak, P. (2003). Dynamic pricing in the presence of inventory considerations: Research overview, current practices, and future directions. Management Science, 49(10), 1287–1309.This foundational review explores how dynamic pricing can be used to manage inventory levels more effectively. Its relevance lies in the connection between pricing decisions and sell-through outcomes, crucial for fashion retail profitability.

Agrawal, N., & Smith, S. A. (2015). Retail supply chain management: Quantitative models and empirical studies (2nd ed.). Springer.Agrawal and Smith provide a comprehensive overview of retail operations and supply chain optimization. Their discussions on inventory allocation and replenishment strategies inform the paper’s recommendations on store-level performance improvement.

Nagle, T. T., & Müller, G. (2017). The strategy and tactics of pricing: A guide to growing more profitably (6th ed.). Routledge.This book outlines core pricing strategies to drive profitability. The concepts help understand why ASP erosion in categories like Denim and Accessories requires a refined approach to maintain perceived value and protect margins.

Choi, T. M., Hecht, G., & Tayur, S. (2020). AI and big data in operations management: A research framework. Operations Research, 68(6), 1449–1461.Choi et al. explore how AI and big data can enhance retail operations and forecasting. Their framework supports the paper’s analytical foundation in using past sell-through data to predict future bestseller categories.

Objectives

• To identify the most profitable category within each menswear category, assessing their sell-through performance and associated dead stock risks.
• To analyze high MRP and low MRP performing styles to understand price-value perception.
• To determine the optimal buying depth for each category to balance inventory efficiency and sales potential.
• To evaluate and compare discounting strategies across categories to understand their impact on margins and inventory liquidation.
• To predict next season's potential bestsellers based on historical data trends (AW’23 to AW’24).
• To identify top-performing and low-performing stores by assessing their sell-through performance.

Research Methodology

This is a quantitative, descriptive, and analytical study. It evaluates category-wise sell-through trends, pricing behavior, and store-level performance across multiple menswear segments using internal company data.The research is based entirely on secondary data from internal sales and inventory records of United Colors of Benetton for the SS’21 to SS’24 and AW’21 to AW’24 seasons.

Data Analysis Techniques

The data analysis involved various techniques, including descriptive statistics such as sell-through percentage, comparative analysis of season-over-season trends, and ASP and MRP band trend analysis. Additionally, store-wise sell-through rate tracking was conducted, and basic forecasting was performed using historical data. The findings were visually represented through charts and tables to facilitate better understanding and decision-making. Data is authentic and consistent, drawn from structured internal records. Findings are repeatable with the same dataset. However, it lacks consumer sentiment data and excludes external market influences.

Limitations

This analysis has several limitations, including the exclusion of qualitative inputs such as customer feedback, which could provide valuable insights. The focus on internal data from a single brand, UCB's menswear business, may also limit the applicability of findings to other brands or product categories. Furthermore, the analysis relies on basic forecasting methods and does not leverage advanced predictive modeling tools. As a result, the conclusions drawn may not be generalizable beyond UCB's menswear business, highlighting the need for more comprehensive and nuanced analysis in the future.

Data Analysis & Interpretation

Category Performance and Sell-Through Trends

The analysis of menswear categories revealed stark disparities in sell-through rates (STR) and pricing dynamics across seasons (23A and 24A). Key findings are summarized below:

Top Performers (STR Growth)

Woven Tops (+6%) and Jackets (+6%) emerged as high-growth categories, driven by strong consumer demand in the mid-premium price range (₹3,300–₹5,800).Accessories (+13%) showed exceptional STR improvement but suffered a 16% decline in ASP, indicating excessive discounting (Figure 1).

Underperformers (STR Decline)

Woven Bottoms (-4%) and Wool (-3%) struggled with low sell-through, particularly at price points like ₹2,999 and ₹5,999, suggesting design or value perception issues (Figure 2).

Figure 1: Category-Wise STR Growth (23A vs. 24A)

Figure 2: ASP Trends by Category

Price Band Analysis

High-Value MRP Ranges

Jackets priced at ₹4,407 achieved a 70% STR in 24A, reflecting strong consumer preference for premium styles.

The ₹3,300–₹5,800 range consistently outperformed, contributing to 43% of total sales in high-performing stores.

Low-Value MRP Ranges

Entry-level price points (₹1,299–₹2,999) in Woven Bottoms and Denim saw STR drops of 10–15%, signalling poor market fit (Figure 3).

High Performing Style

Figure 3: MRP-Wise STR for Jackets

Low Performing Style

Store-Level Performance Disparities

Top Stores:

Hyderabad Airport (+68% STR) and Bangalore Lulu (+73% STR) excelled, attributed to localized assortments and high footfall.

Underperforming Stores:

Oberoi Gurgaon an Infinity Mall Mumbai recorded 0% STR, highlighting inventory mismatches (Figure 4).

Figure 4: Store-Wise STR Heatmap

Discounting Impact on Margins

• Effective Liquidation: Discounts improved STR for Denim(+5%) and Knit Bottoms (+5%) but eroded margins (ASP declines of 12% and 8%, respectively).
• Controlled Discounting: Categories like Jackets(ASP +3%) minimized markdowns, preserving profitability (Figure 5).

Figure 5: Discount Allocation by Category

PREDICTIVE INSIGHTS FOR AW25

Bestseller Candidates - Woven Tops (70,607 units sold) and Polo (49,951 units) are projected to dominate, with realization rates growing by 6.8%.

Inventory Optimization- A 60% STR target for AW25 recommends leaner buys in declining categories (e.g., Woven Bottoms) and expanded depth for high-STR items (Figure 6).

Figure 6: Recommended Buying Depth for AW25

Findings & Suggestions

The findings reveal varying performance across product categories, with Woven Tops and Jackets achieving high sell-through rates (STR), while Wool and Woven Bottoms lag. Average Selling Price (ASP) has dropped in Accessories and Denim, likely due to excessive discounting. The mid-premium price segment (₹3,300–₹5,800 MRP) has shown strong performance. Additionally, significant disparities exist at the store level, with airport stores outperforming while city stores remain stagnant, highlighting opportunities for targeted improvement and optimization.

Suggestions

It is suggested to invest in price bands with consistent sell-through rates. Low-performing styles, particularly in the ₹1,299–₹2,999 and ₹5,999+ segments, should be reworked. Inventory should be reallocated from underperforming stores with 0% sell-through rates to better-performing locations. Strategic markdown control should be introduced to protect Average Selling Price (ASP). The sell-through trends should be leveraged for predictive planning in the upcoming Autumn/Winter 2025 season to inform inventory and pricing decisions.

Conclusion

This study highlights the importance of data-driven decision-making in menswear retail. By leveraging sell-through rates, Average Selling Price trends, and store-level performance, United Colors of Benetton can optimize its product offerings, pricing, and inventory allocation. By implementing the suggested strategies, the brand can improve profitability, reduce markdowns, and better align with customer demand, ultimately driving success in the competitive fashion market. With a focus on pricing discipline and targeted inventory planning, UCB can enhance its competitiveness and drive growth. By adopting a predictive approach to planning, the brand can stay ahead of seasonal trends and consumer preferences. This data-driven strategy will enable UCB to make informed decisions and respond effectively to market dynamics. The insights from this analysis can serve as a foundation for sustained growth and profitability in the menswear segment.

References

• Agrawal, N., & Smith, S. A. (2015). Retail supply chain management: Quantitative models and empirical studies (2nd ed.). Springer.
• Cachon, G. P., & Swinney, R. (2011). The value of fast fashion: Quick response, enhanced design, and strategic consumer behavior. Management Science, 57(4), 778–795.
• Chen, W., Murray, R., & Van Wassenhove, L. N. (2013). Assortment planning for retailers using store-level transaction data. Operations Research, 61(5), 1030–1047.
• Choi, T. M., Hecht, G., & Tayur, S. (2020). AI and big data in operations management: A research framework. Operations Research, 68(6), 1449–1461.
• Elmaghraby, W., &Keskinocak, P. (2003). Dynamic pricing in the presence of inventory considerations: Research overview, current practices, and future directions. Management Science, 49(10), 1287–1309.
• Fisher, M. L., Gallino, S., & Li, J. (2017). Competition-based dynamic pricing in online retailing: A methodology validated with field experiments. Management Science, 64(6), 2496–2514.
• Kwon, W. S., Ha-Brookshire, J. E., & Norum, P. (2020). Predictive analytics for assortment planning in fashion retailing. Journal of Retailing and Consumer Services, 53, 101962.
• Lee, H. L., & Tang, C. S. (2017). Socially and environmentally responsible value chain innovations: New operations management research opportunities. Management Science, 63(3), 721–734.
• Nagle, T. T., & Müller, G. (2017). The strategy and tactics of pricing: A guide to growing more profitably (6th ed.). Routledge.