Innovation Owner
Mr. PHARADON SAPMANKHONGSIN
Student
Details
This study compares the performance of four machine learning methods—Decision Tree, Random Forest, KNN, and SVM—in time series forecasting using lagged time intervals as independent variables.
This special problem aims to compare the performance of machine learning methods in time series forecasting using lagged time periods as independent variables. The lagged periods are categorized into three groups: 10, 15, and 20 units. The study employs four machine learning methods:
- Decision Tree (DT)
- Random Forest (RF)
- K-Nearest Neighbors (KNN)
- Support Vector Machine (SVM)
The research uses simulated time series data with diverse characteristics, including Random Walk, Trending, and Non-Linear data, with sample sizes of 100, 300, 500, and 700. Simulations and analysis were performed using the R programming language with 1,000 iterations. The results are evaluated based on the average mean squared error (AMSE) and the average mean absolute percentage error (AMAPE) to identify the best-performing method.
Objective
To study and compare the performance of four machine learning methods in analyzing time series data using lagged time intervals.
- To study time series data using lagged time intervals with machine learning methods, including Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM).
- To compare the performance of time series data analysis using lagged time intervals with machine learning methods, including Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM).