Tick based clustering methodologies establishing support and resistance levels in the currency exchange market
(2020) In National Accounting Review 2(4). p.354-366- Abstract
- We establish support and resistance levels from data in intraday currency exchange market activity based on machine learning methods. Specifically we design two semi-supervised classification neural networks. The first one is based on a variant of the K-means method while the second is based on a Gaussian mixture model with expectation maximisation. Each performs classification from tick data on very short time windows and produces the corresponding support and resistance price levels. We test the methodology on actual market data for the EUR-USD currency exchange. As a sanity check we also perform mock trades based on actual market data. We evaluate the results for statistical significance using a number of performance metrics while also... (More)
- We establish support and resistance levels from data in intraday currency exchange market activity based on machine learning methods. Specifically we design two semi-supervised classification neural networks. The first one is based on a variant of the K-means method while the second is based on a Gaussian mixture model with expectation maximisation. Each performs classification from tick data on very short time windows and produces the corresponding support and resistance price levels. We test the methodology on actual market data for the EUR-USD currency exchange. As a sanity check we also perform mock trades based on actual market data. We evaluate the results for statistical significance using a number of performance metrics while also comparing against traditional methods. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/696175bc-f71c-4b22-96b9-99ddbb26cc4e
- author
- Tengelin, Karl and Sopasakis, Alexandros LU
- organization
- publishing date
- 2020-10-23
- type
- Contribution to journal
- publication status
- published
- subject
- in
- National Accounting Review
- volume
- 2
- issue
- 4
- pages
- 13 pages
- publisher
- AIMS Press
- ISSN
- 2689-3010
- DOI
- 10.3934/NAR.2020021
- language
- English
- LU publication?
- yes
- id
- 696175bc-f71c-4b22-96b9-99ddbb26cc4e
- date added to LUP
- 2021-02-02 22:31:40
- date last changed
- 2021-05-05 15:20:39
@article{696175bc-f71c-4b22-96b9-99ddbb26cc4e, abstract = {{We establish support and resistance levels from data in intraday currency exchange market activity based on machine learning methods. Specifically we design two semi-supervised classification neural networks. The first one is based on a variant of the K-means method while the second is based on a Gaussian mixture model with expectation maximisation. Each performs classification from tick data on very short time windows and produces the corresponding support and resistance price levels. We test the methodology on actual market data for the EUR-USD currency exchange. As a sanity check we also perform mock trades based on actual market data. We evaluate the results for statistical significance using a number of performance metrics while also comparing against traditional methods.}}, author = {{Tengelin, Karl and Sopasakis, Alexandros}}, issn = {{2689-3010}}, language = {{eng}}, month = {{10}}, number = {{4}}, pages = {{354--366}}, publisher = {{AIMS Press}}, series = {{National Accounting Review}}, title = {{Tick based clustering methodologies establishing support and resistance levels in the currency exchange market}}, url = {{http://dx.doi.org/10.3934/NAR.2020021}}, doi = {{10.3934/NAR.2020021}}, volume = {{2}}, year = {{2020}}, }