Abstract

Due to new technologies, sales forecasting has become increasingly popular as a way to improve market operations and productivity in the retail industry. Although the business has historically concentrated on a stand-ard statistical model, machine-learning techniques have garnered increased attention in recent years. A key com-ponent of retail is store sales. The most trustworthy models are scrutinized by administrators in order to help fore-cast future sales. Making decisions based on historical and present data might be facilitated by forecasting future variations or increases in store sales. By recognizing sales patterns and trends, accurate forecasting will help busi-nesses or retailers increase profitability and enhance the customer experience. Predicting retail store sales with deep learning and machine learning (ML) approaches yields high. This study summarizes ML techniques to identify the best algorithm for predicting retail sales based on a collection of prior research articles. This work detects the most influencing attributes that affect sales, and suitable ML algorithms for sales forecasting.