html_document

GVC

PROGRAMMING FOR DATA SCIENCE OCC3 WQD7004 Group project submission Dataset link: https://www.kaggle.com/datasets/yusufdelikkaya/datascience-salaries-2024

This study explores the application of machine learning models for predicting house prices, comparing the performance of traditional regression techniques (Linear, Ridge, and Lasso) with advanced ensemble methods (Random Forest and XGBoost). The findings reveal that ensemble models, particularly XGBoost, outperform traditional methods, achieving the lowest RMSE of 0.4069. Key predictors identified include **distance to MRT**, **house age**, and **latitude**, with proximity to transportation being the most significant factor influencing house prices. The study underscores the efficacy of ensemble techniques in capturing complex relationships, offering valuable insights for real estate forecasting and decision-making.

Title: Enhancing Customer Retention in a Telecommunication Company Through Service Usage and Churn Analysis

This study explores the application of machine learning models for predicting house prices, comparing the performance of traditional regression techniques (Linear, Ridge, and Lasso) with advanced ensemble methods (Random Forest and XGBoost). The findings reveal that ensemble models, particularly XGBoost, outperform traditional methods, achieving the lowest RMSE of 0.4069. Key predictors identified include **distance to MRT**, **house age**, and **latitude**, with proximity to transportation being the most significant factor influencing house prices. The study validates the efficacy of ensemble techniques in capturing complex relationships, offering valuable insights for real estate forecasting and decision-making.

Test