Decision support system for stock market by using neural network

Name: Sabaithip Boonpeng

Organization : Mae Fah Luang University

keyword: Neural network

LCSH: Neural networks (Computer science)

Classification :.LCCS: QA76.87

Abstract: Stock investment is a trading activity, which can provide a high return. The challenging task of investors is how to select a good stock and achieve a great return. Several factors affect stock movements such as a market value risk, a political risk and an economic risk. These factors can control the stock price and they are also difficult to be predicted in the current situation. Generally, investors use two techniques on trading. These are fundamental analysis and technical analysis techniques. Presently, several machine learning models are increasingly applied to analyze the stock trading prediction, for example, Genetic Algorithms (GAs), Linear Regression (LR), Support Vector Machines (SVMs) and Artificial Neural Network (ANN). In this thesis, a stock trading prediction model by using historical stock data is proposed and developed. ANN is used as a multiclass classification technique. Furthermore, the complexity of model of multiclass classification problems is reduced by transforming to a simple form of binary-class problem. In multi-binary classification experiments, One-Against-One (OAO) and One-Against-All (OAA) techniques are employed and compared with traditional ANN model. The experimental results show that the multi-binary classification using OAA technique can provide better predictive results than other techniques. Moreover, the performance of multi-binary classification using the OAA technique is tested by a back testing method in order to evaluate the return on investment. The results present that the proposed model can generate the return on investment greater than other traditional analysis techniques.

Mae Fah Luang University. The Learning Resources and Education Media Center

Address: Chiang Rai

Email: library@mfu.ac.th

Name: Piyasak Jeatrakul

Role: Advisor

Created: 2016

Issued: 2017

Modified: 2020-04-27

Issued: 2017-04-10

วิทยานิพนธ์/Thesis

application/pdf

CallNumber: Thesis QA76.87 S113d 2016

eng

DegreeName: Master of Science

Level: Master's Degree

Descipline: Information Technology

Grantor: Mae Fah Luang University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	Sabaithip Boonpeng.pdf	1.44 MB	26	2025-08-24 13:21:25

ใช้เวลา

0.014926 วินาที