Data Mining Using Extended LASSO-based Factor Selection Algorithms

Please enable javascript in your browser.

Javadi Narab, Nahid | 2020

437 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 53364 (01)
University: Sharif University of Technology
Department: Industrial Engineering
Advisor(s): Akhavan Niaki, Taghi
Abstract:
Today, with the development of financial and economic sciences and the increasing volume of financial data, it is necessary to process and analyze this field more accurately with up-to-date tools. On the other hand, by the significant growth of the use of machines and computers for analysis and forecasting purposes, their importance and application have been well defined. Therefore, this research is considered to provide a more efficient method by processing historical data and analyzing them using data mining techniques. The results of this study can be provided to experts in this field as an effective method. Therefore, in this research, a new method based on the selection of required variables using Lasso regression technique and Gibbs sampling has been introduced. This regression technique tries to provide a suitable method for modeling the response variable based on the minimum and of course the most appropriate number of independent variables. Also, this research is provided to implement vector autoregressive models on a time series dataset to forecast and then compare accuracy of models.
Keywords:
Data Mining ; Support Vector Machine (SVM) ; Bagging ; Prediction ; Boosting Machine Learning ; Least Absolute Shrinkage and Selection Operator (LASSO) Estimator ; Bayesian Method

No TOC