Year: 2025
Type: article
Abstract: —(1)Sales forecasting is a critical component of business strategy and inventory management, enabling organizations to make informed decisions based on future market demand. (2)This research explores the application of machine learning algorithms for improving the accuracy and efficiency of sales forecasting. (3)By analyzing historical sales data, external factors such as seasonal trends, promotions, and economic indicators, the study implements and evaluates various machine learning models including Linear Regression, Decision Trees, Random Forest, and Long Short-Term Memory (LSTM) neural networks. (4)The comparative analysis reveals that advanced models like LSTM outperform traditional statistical methods by capturing temporal dependencies and nonlinear patterns in the data. (5)The study also integrates data preprocessing techniques, feature engineering, and model tuning to enhance prediction performance. (6)Experimental results demonstrate that machine learning-based forecasting not only improves accuracy but also enables dynamic, real-time adaptability for businesses. (7)This work contributes to the growing body of knowledge on AI-driven decision-making, paving the way for smarter, data-informed business operations. Keywords— sales forecasting, machine learning, LSTM, time series, regression, inventory management, demand prediction, business intelligence.
DOI: 10.55041/ijsrem48670
Author: Shivam Agrahari
Institution: IIMT College of Engineering, Greater Noida
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: bronze
OpenAlex ID: W4410745347