Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/358825
Title: | Machine learning techniques applied for the analysis of financial and energy markets |
Researcher: | DAS,PRAGYAN PARAMITA |
Guide(s): | Dash,P.K. and Bisoi,Ranjeeta |
Keywords: | Computer Science Computer Science Interdisciplinary Applications Engineering and Technology |
University: | Siksha quotOquot Anusandhan University |
Completed Date: | 2021 |
Abstract: | The focus of the thesis is to analyze financial and energy markets which are very newlinecomplex markets. In financial market, stock price prediction and currency exchange rate newlineprediction are two important indices and are nonlinear and non-stationary in nature. In newlineenergy market, electricity price prediction is an important factor time series like currency newlineexchange rate, stock price prediction newlineA lot of research has been done in the prediction of such complex markets. newlineNumerous machine learning methods have been applied in this direction in order to newlinedevelop better prediction models. Still there is increasing demands for improved newlinemethods in the search of better forecasting models. In this work, different attempts have newlinebeen made to propose improved prediction models for financial and energy market newlineprediction i.e. the prediction of stock price / currency exchange price and movement newlinedirection prediction (trend) / electricity price prediction and classification. Machine newlineintelligence techniques and soft computing methods have been applied for developing newlinesimple and robust prediction models for the purpose. As machine learning techniques are newlinemore capable and powerful with better generalization ability and universal newlineapproximation, they are proved to be better solution in non-linear time series analysis. newlineBy taking the advantage of machine learning techniques three models have been newlinedeveloped in the thesis for accurate future price prediction. Both regression and newlineclassification problems have been taken into consideration. Using the developed models newlineaccurate prediction / classification is accomplished with significantly accurate results. newlineThe developed models are: newlineand#61623; Time Series Forecasting Using Fuzzy Functional Link Neural Network newlineTrained By Improved Second Order Levenberg-Marquardt Algorithm. newlineand#61623; Data Decomposition based Fast Reduced Kernel Extreme Learning Machine newlinefor Currency Exchange Rate Forecasting and Trend Analysis newlineand#61623; Short-Term Electricity Price Forecasting and Classification in Smart Grids using Optimized Multi Kernel Extreme Le |
Pagination: | xx,151 |
URI: | http://hdl.handle.net/10603/358825 |
Appears in Departments: | Department of Computer Science |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 290.28 kB | Adobe PDF | View/Open |
02-declaration.pdf | 133.11 kB | Adobe PDF | View/Open | |
03_certificate.pdf | 127.71 kB | Adobe PDF | View/Open | |
04_acknowledgement.pdf | 133.15 kB | Adobe PDF | View/Open | |
05_contents.pdf | 146.96 kB | Adobe PDF | View/Open | |
06_list of figures and table.pdf | 139.35 kB | Adobe PDF | View/Open | |
07_chapter 1.pdf | 265.71 kB | Adobe PDF | View/Open | |
08_chapter 2.pdf | 377.66 kB | Adobe PDF | View/Open | |
09_chapter 3.pdf | 712.28 kB | Adobe PDF | View/Open | |
10_chapter 4.pdf | 850.52 kB | Adobe PDF | View/Open | |
11_chapter 5.pdf | 141.12 kB | Adobe PDF | View/Open | |
12_bibliography.pdf | 251.29 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 174.43 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: