Multi-level Pattern Prediction of Unstructured Financial Data: Extended Hidden Markov Decision Model Prediction System

Akinbode, Kayode

ISBN 10: 6200258171 / ISBN 13: 9786200258175

Published by LAP LAMBERT Academic Publishing, 2019

About this Item

140 pages. 8.66x5.91x0.32 inches. In Stock.

Seller Inventory # zk6200258171

Bibliographic Details

• Title: Multi-level Pattern Prediction of Unstructured Financial Data: Extended Hidden Markov Decision Model Prediction System
• Publisher: LAP LAMBERT Academic Publishing
• Publication Date: 2019
• Language: English
• ISBN 10: 6200258171
• ISBN 13: 9786200258175
• Binding: Paperback
• Condition: Brand New
• Weight: 0.25 kilograms

About this title

Synopsis

Predicting the future is one aspect in designing profitable day trading strategies. Technical analysis analyses price, volume and other market information, whereas fundamental analysis looks at the facts of the company, market, currency or commodity. Most large brokerage, trading group, or financial institutions will typically have both a technical analysis and fundamental analysis team. Technical analysis is considered for the research work. The design of HMDM based stock market trend prediction system and the EHHMM for predicting the future trend of the CBOE and Nigerian 7up bottling company data is presented in this research work. Features are extracted from the historical CBOE closing price data. Extracted features are used to generate the prediction. HHMMs are useful in applications dealing with sequences of symbols. It is observed by study that the EHMDM based system is more accurate than the HMDM based system. It was observed that the EHMDM combined with EST prediction system produces a better accuracy. The HMDM combined with MAT prediction system, with hidden states, produced a lower accuracy. It can be concluded from the present study that prediction system with EHMDM