An Experimental Study on Prediction of Revenue and Customer Segmentation

The proliferation of product variety presents a significant challenge for small retailers grappling with limited space and capital to manage their inventory effectively. This paper addresses this issue by investigating various machine learning and deep learning algorithms for predicting future produ...

Full description

Saved in:
Bibliographic Details
Published in2024 8th International Conference on Inventive Systems and Control (ICISC) pp. 500 - 506
Main Authors Mikkilineni, Bhavya Sai, Madala, Uuhasri, Bonthagorla, Renu Sree, Parikala, Yashmitha Priya, Venkatrama Phani Kumar, S, KishoreK, Venkata Krishna
Format Conference Proceeding
LanguageEnglish
Published IEEE 29.07.2024
Subjects
Clustering algorithms
Customer Segmentation
Deep learning
Machine learning algorithms
Operational Performance
Propulsion
Retail Industry
Revenue Forecasting
Supply chains
Time series analysis
Uncertainty
Online AccessGet full text

Cover

More Information
Summary:The proliferation of product variety presents a significant challenge for small retailers grappling with limited space and capital to manage their inventory effectively. This paper addresses this issue by investigating various machine learning and deep learning algorithms for predicting future product demand in small retail establishments. Accurate demand forecasts are crucial not only for optimizing retail operations but also for enhancing the efficiency of the entire supply chain. Leveraging the abundance of data available today, this study explores the application of suitable machine learning algorithms for forecasting, thereby enabling small retailers to maximize their profit margins. In addition to sales forecasting, the research aims to conduct customer segmentation, facilitating informed decision-making to drive revenue generation. By harnessing predictive analytics, small retail shop owners can make strategic decisions that align with market demand and consumer behavior, thereby enhancing their competitiveness in the retail landscape.
DOI:10.1109/ICISC62624.2024.00089