A Web-Based Analytics-Based Intelligent Machine Learning Framework for Forecasting Consumer Purchase Behaviour
- Version
- Download 3
- File Size 280.88 KB
- File Count 1
- Create Date 24 March 2026
- Last Updated 24 March 2026
A Web-Based Analytics-Based Intelligent Machine Learning Framework for Forecasting Consumer Purchase Behaviour
Dr. K. Satyam1, Kalamala Kavya2
1Associate Professor, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, AndhraPradesh, India.
2 Post Graduate, Department of MCA, Annamacharya Institute of Technology & Sciences, Tirupati, AndhraPradesh, India.
Abstract:Forecasting consumer purchase behaviour has become crucial for businesses hoping to promote sales and customer engagement. This paper presents a machine learning-based method for analysing and predicting consumer purchase decisions using behavioural data. The proposed method uses factors including user visits, time spent on the platform, cart additions, and previous purchase history to calculate the likelihood of a purchase. A Gradient Boosting Classifier is employed as the primary model due to its exceptional accuracy and ability to handle complex patterns in structured data. The model is integrated into a Flask-based web application that anticipates and visualises significant influencing factors in real time using an interactive dashboard. Experiments have shown that behavioural traits, particularly cart additions and time spent, have a significant impact on purchase intent. The technology provides helpful data that businesses can utilise to improve customer happiness and develop targeted marketing strategies. This study demonstrates the value of machine learning techniques in understanding consumer behaviour and supporting data-driven decision-making.
Keywords:Customer purchase prediction, machine learning, gradient boosting, customer behavior analysis, web analytics, classification, Flask application, predictive modeling, feature importance, e-commerce analytics
Download