Future–Proofing e-Commerce: Innovative Sales Forecasting with Regression and Time Series Models

View at publisher Summarise with VIRAT
Authors: P. Nanthitha, G. Subhashini, K. Sangeetha, C. M. Varun
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Consumers can now access the global market and use a wide-ranging internet connection for an infinite number of purchasing options thanks to modern e-commerce. This results in the fierce competition unprecedented particularly within the e-commerce platforms. We can use this advanced sales forecast to know our customers much better as it is imperative to get ahead of the competition. This anticipates sales of commodities in the market in future. Some of the algorithms that are utilized in machine learning include time series and regression algorithms. This algorithm considers behavior of consumers, market trends, historical sales data and external factor may include environment and economic trends to be able to predict future sales. It makes unique recommendations to customers (customer-specific) and gives you in-time customer knowledge to maximize accuracy levels. By forecasting our future product demand, we can become competitive, be future-proof, and increase our e-commerce business. Keywords Customer behavior e-commerce, past sales data, market pattern, machine learning, regression.

Fields of Study & Subjects

Forecasting Techniques and Applications Time Series Analysis and Forecasting Big Data and Business Intelligence

Publication details

Journal / source
CRC Press eBooks
Pages
169–174
Publication date
26 March 2026
Language
EN
Document type
Book chapter