NORMA eResearch @NCI Library

Behavioral Modelling of Customer Marketing Patterns and Review Prediction Using Machine Learning Techniques

Chate, Pratiksha Arvind (2022) Behavioral Modelling of Customer Marketing Patterns and Review Prediction Using Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Technology has enabled businesses to produce a wide range of products that can dazzle clients, but customers are befuddled by the variety of choices available. While the retail industry faces several issues in terms of customer attention and loyalty, there is a need to improve marketing strategies. This study aims to segment the customers based on their purchasing patterns with RFM modelling and predict the review score for next order. The binary classification is performed to classify the reviews as positive (review score greater than 3) or negative (review score less than or equal to 3). Detailed analysis of the data have been performed on the Olist e-commerce dataset available publicly on Kaggle. New time-based and distance-based features were created from the existing attributes that were found to be useful for the prediction of review score. Machine learning classification models such as Random Forest, Light Gradient Boosting Model (LGBM) and AdaBoost model were implemented on the randomly oversampled data. The Random Forest Model outperformed other classification models with 95% accuracy and the F1-score of 0.95 for positive and negative class. This approach was found to be successful for detecting the review score and compared well with previous work in the field.

Item Type: Thesis (Masters)
Uncontrolled Keywords: AdaBoost; LGBM; Random Forest; RFM modelling; review prediction
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HF Commerce > Marketing > Consumer Behaviour
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
H Social Sciences > HF Commerce > Marketing
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 Jan 2023 16:31
Last Modified: 06 Mar 2023 13:45

Actions (login required)

View Item View Item