NORMA eResearch @NCI Library

Hyperparameter Tuning for the Prediction of Customer Revenue

Mehta, Rutuja Dinesh (2022) Hyperparameter Tuning for the Prediction of Customer Revenue. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Owning to cutthroat competition, the business ecosystem is paying increasing attention to customer relationship management (CRM). To build successful customer retention strategies, it is essential to optimize their lifetime value. Building an analytical data model that integrates financial, marketing, and advertising data to forecast the return on advertising across many scenarios is vital. The model should depict the revenue flow resulting from customer interactions at the top of the funnel by including the early marketing expenditure. Inspired by a recent Kaggle competition in 2019, we set out to identify profitable customers and predict their revenue. A range of Machine Learning and Deep Learning models were implemented and evaluated their performance based on the RMSE. We will show how the proposed methodology allows us to obtain better results than the winners of the Kaggle competition. Light Gradient Boost Model (LGBM) performed better than the rest giving the RMSE value of 0.95 after tuning the hyperparameter using the Random Search Cross-Validation technique. The model gives excellent results for classifying low and high-revenue generating customers, making a guideline for sale and marketing strategies.

Item Type: Thesis (Masters)
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: 23 Feb 2023 12:32
Last Modified: 02 Mar 2023 09:18

Actions (login required)

View Item View Item