Author Name
Princy Chouksey, Vishwa Gupta, Bhawana Pillai, Bhupesh Gour
Abstract
In today’s data-driven marketplace, the ability to accurately forecast sales plays a vital role in strategic decision-making and business planning. This paper presents a comparative analysis of various machine learning models—Linear Regression, Random Forest, XGBoost, and Long Short-Term Memory (LSTM)—to predict market sales trends. The models were evaluated using standard performance metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and R² Score. Experimental results indicate that traditional models like Linear Regression are limited in capturing complex market patterns, whereas advanced models such as XGBoost and LSTM provide significantly better accuracy. Among them, the LSTM model achieved the best performance, demonstrating its strength in handling sequential sales data and delivering highly reliable forecasts. This study highlights the potential of integrating deep learning and ensemble techniques to improve predicti