Forecasting market movement in Dhaka Stock Exchange: LSTM vs. ARIMA

Simple item page
dc.contributor.advisorKhan, Wasiqur Rahman
dc.contributor.authorChakraborty, Pranjal
dc.date.accessioned2019-07-11T04:32:17Z
dc.date.available2019-07-11T04:32:17Z
dc.date.issued2019-04
dc.descriptionCataloged from PDF version of thesis.
dc.descriptionIncludes bibliographical references (pages 34-35).
dc.descriptionThis thesis is submitted in a partial fulfillment of the requirements for the degree of Masters of Science in Applied Economics, 2019.
dc.description.abstractThis paper creates and examines the performance of LSTM models against ARIMA models, using Dhaka Stock Exchange data from beginning of 2000 to the beginning of 2019. An algorithm has been designed to simultaneously train and test the models using datasets of 340 companies of the market. The empirical result shows the absolute dominance of ARIMA over LSTM, which contradicts some previous works. At the end, we try to discuss the possible reasons behind the unsatisfactory performance of LSTM and explore some of the possible future expansions and extensions of the current work.
dc.identifier.otherID 18175001
dc.identifier.otherhttps://dspace.bracu.ac.bd/server/api/core/items/5e1a0345-5c3a-4a18-8847-3538ea31a0a0
dc.identifier.urihttp://hdl.handle.net/10361/12335
dc.language.isoen
dc.publisherBRAC University
dc.sourceBRAC University Institutional Repository
dc.subjectLong short-term memory
dc.subjectAutoregressive integrated moving average
dc.subjectEconometrics
dc.subjectData mining
dc.subjectDeep learning
dc.subjectNeural network
dc.subjectMachine learning
dc.subjectDhaka Stock Exchange
dc.subjectCapital market
dc.subjectArtificial intelligence
dc.titleForecasting market movement in Dhaka Stock Exchange: LSTM vs. ARIMA
dc.typeThesis

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
18175001.pdf
Size:
2.15 MB
Format:
Adobe Portable Document Format
Download

Collections

Thesis (Master of Science in Applied Economics)