Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476389Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Masnizah Mohd, Dr. | |
| dc.contributor.author | Abuhamad Mohammed I. S. (P57886) | |
| dc.date.accessioned | 2023-10-06T09:17:36Z | - |
| dc.date.available | 2023-10-06T09:17:36Z | - |
| dc.date.issued | 2013-03-06 | |
| dc.identifier.other | ukmvital:84863 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476389 | - |
| dc.description | Forex market is the most liquid financial market and the largest market in the world. In forex, traders try to gain insight into the market by analysing all determinants and factors which may affect the market state and the price movement. Two basic approaches are commonly used to analyse forex market: technical analysis which aims to forecast the movement of exchange rate price by studying the past data of the market; and fundamental analysis which concerns essentially with the overall state of the economy. Designing any decision support system for forex trading is supposed to have the capability to capture the relations associating with related factors in forex environment and turn them into useful knowledge. This research aims to develop an event-driven business intelligence approach to generate a trading signals based on different strategies. It integrates both technical and fundamental analysis and predicts the future state of the market. Based on theoretical study, the general framework of proposed system is designed addressing three major parts: gathering information, gaining insight and generating trading signals. Based on quantitative or qualitative perspective, different machine learning models have been built to response to upcoming information. The historical quantitative data is used to build the exchange rate and macroeconomic indicators predictors based on Artificial Neural Networks and Genetic Programming. Whereas qualitative knowledge is used to guide the decision making process and to build a knowledge-based model to generate trading signals based on expert domain consultation. For overall system evaluation, many experiments are carried out to define the best trading strategy according to the number of exchange rates timeframes considered on the decision process and the value of adding external factors. The results indicate that using multi-timeframe strategy to generate exchange rate signals would be less risky than using only one timeframe data. However, considering external factors would enhance the quality of decision and generate reliable trading signals. This results show a promising direction for the proposed system and its ability to accept additional external factors and consider them in the decision process.,Master / Sarjana | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Forex market | |
| dc.subject | Financial market | |
| dc.subject | Neural networks (Computer science) | |
| dc.title | Event-driven approach for real-time integration of fundamental and technical analysis in forex market | |
| dc.type | theses | |
| dc.format.pages | 110 | |
| dc.identifier.callno | QA76.54.A256 2013 | |
| dc.identifier.barcode | 002018 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_84863+SOURCE1+SOURCE1.0.PDF Restricted Access | 2.88 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.