Predicting Customer Lifetime Value: A Comprehensive Approach with Machine Learning and Deep Learning Models

Joy, Arun (2024) Predicting Customer Lifetime Value: A Comprehensive Approach with Machine Learning and Deep Learning Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (952kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Predicting Customer Lifetime Value (CLV) is important for marketing to manage customer relationships. Traditional models mostly struggle with the high dimensional type of data, so this study is centered on forecasting the Customer Lifetime Value (CLV) using a dataset from Kaggle which contains detailed customer information that enables interpretation of demographic and purchasing patterns. The pre-processing steps include removing unimportant features, converting categorical data into numerical data with the help of Label Encoder while normalizing the data with the help of MinMaxScaler. The selection of the features is done to select the top 10 important features that have a high influence on predicting CLV using feature importance methods. The dataset is then split into training and testing sets in the 80:20 ratio for model training. Modelling encompasses Decision Tree Regression, Random Forest Regression, Gradient Boosting Regression, GRU-LSTM and Bidirectional LSTM with Attention Mechanism model. For the performance comparison of these models, MSE, RMSE and R² Score are used. At last, it was perceived that the Bidirectional LSTM model with Attention Mechanism is the most efficient among all other models with the value of R² of 0.94.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Singh, Jaswinder UNSPECIFIED
Uncontrolled Keywords:	Customer Lifetime Value (CLV); Machine Learning; Deep Learning; Decision Tree Regression; Random Forest Regression; Gradient Boosting Regression; GRU-LSTM; Bidirectional LSTM (BiLSTM)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management > Human Resource Management > Performance Management
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 15:09
Last Modified:	02 Sep 2025 15:09
URI:	https://norma.ncirl.ie/id/eprint/8719

Actions (login required)

View Item