Peek into the future: Artificial intelligence in forecasting the 8 PSE indices

Date of Publication

2016

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Management of Financial Institutions

Subject Categories

Finance and Financial Management

College

Ramon V. Del Rosario College of Business

Department/Unit

Financial Management

Thesis Adviser

Mar Andriel Umali

Defense Panel Member

Tyrone Chan Pao
Ricarte Pinlac

Abstract/Summary

This study explores the use of artificial intelligence in stock market prediction. Recent studies have reported that artificial intelligence outperforms traditional techniques when it comes to accuracy performance in forecasting. In this paper, the researchers only focused on the two most known models of artificial intelligence, which are artificial neural network (ANN) and support vector machine (SVM). These models were trained on the 8 indices of the Philippine Stock Exchange, namely, PSEi, all shares, financials, industrial, holding firms, services, mining and oil, and property. Technical and macroeconomic variables from years 2010 to the first quarter of 2016 were used as inputs. The researchers examined and compared the performance of ANN and SVM in forecasting stock price and direction movement. By using paired T-test, RMSE/MAE/MAE and hit miss test in forecasting the value of the 8 indices, it was found that both model can forecast, however, ANN performs better than SVM. Direction symmetry test, on the other hand, showed that ANN and SVM have low accuracy performance in forecasting the direction of the indices. This research will be of great use to market participants who seek new methods in forecasting the Philippine stock market.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU01017

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

144, [4] leaves : illustrations ; 28 cm. + 1 computer disc ; 4 3/4 in.

Keywords

Stock price forecasting--Philippines; Stock price forecasting--Data processing

This document is currently not available here.

Share

COinS