Difference between revisions of "The EMH for Bitcoin in the context of neural networks"
(Created page with "== Details == * Authors: Mike Krähenbühl * Title: The efficient market hypothesis for Bitcoin in the context of neural networks * Supervisior: Prof. Dr. Jörg Osterrieder *...") |
|||
| (5 intermediate revisions by the same user not shown) | |||
| Line 13: | Line 13: | ||
== Abstract == | == Abstract == | ||
| − | This study examines the weak form of the efficient market hypothesis for Bitcoin using a feedforward neural network. Due to the increasing popularity of cryptocurrencies in recent years, the question has arisen, as to whether market inefficiencies could be exploited in Bitcoin. Several studies we refer to here discuss this topic in the context of Bitcoin using either statistical tests or machine learning methods, mostly relying exclusively on data from Bitcoin itself. Results regarding market efficiency vary from study to study. In this study, however, the focus is on applying various asset-related input features in a neural network. The aim is to investigate whether the prediction accuracy improves when adding equity stock indices (S | + | This study examines the weak form of the efficient market hypothesis for Bitcoin using a feedforward neural network. Due to the increasing popularity of cryptocurrencies in recent years, the question has arisen, as to whether market inefficiencies could be exploited in Bitcoin. Several studies we refer to here discuss this topic in the context of Bitcoin using either statistical tests or machine learning methods, mostly relying exclusively on data from Bitcoin itself. Results regarding market efficiency vary from study to study. In this study, however, the focus is on applying various asset-related input features in a neural network. The aim is to investigate whether the prediction accuracy improves when adding equity stock indices (S&P 500, Russell 2000), currencies (EURUSD), 10 Year US Treasury Note Yield as well as Gold&Silver producers index (XAU), in addition to using Bitcoin returns as input feature. As expected, the results show that more features lead to higher training performance from 54.6% prediction accuracy with one feature to 61% with six features. On the test set, we observe that with our neural network methodology, adding additional asset classes, no increase in prediction accuracy is achieved. One feature set is able to partially outperform a buy-and-hold strategy, but the performance drops again as soon as another feature is added. This leads us to the partial conclusion that weak market inefficiencies for Bitcoin cannot be detected using neural networks and the given asset classes as input. |
Therefore, based on this study, we find evidence that the Bitcoin market is efficient in the sense of the efficient market hypothesis during the sample period. We encourage further research in this area, as much depends on the sample period chosen, the input features, the model architecture, and the hyperparameters. | Therefore, based on this study, we find evidence that the Bitcoin market is efficient in the sense of the efficient market hypothesis during the sample period. We encourage further research in this area, as much depends on the sample period chosen, the input features, the model architecture, and the hyperparameters. | ||
== Important links == | == Important links == | ||
| − | * [https://de.overleaf.com/read/txchcpqbbpdx] | + | * [https://de.overleaf.com/read/txchcpqbbpdx Overleaf] |
| − | * [https://github.com/mikekraehenbuehl/BA_2022_Neural_Network_Bitcoin] | + | * [https://github.com/mikekraehenbuehl/BA_2022_Neural_Network_Bitcoin GitHub] |
| + | * [https://drive.google.com/drive/folders/1E2sGajWczI4jgBBEKfqNORDO1oWQv3M2 Google Drive with paper and links] | ||
| + | * [https://arxiv.org/abs/2208.07254 Arxiv] | ||
== Data == | == Data == | ||
| Line 28: | Line 30: | ||
* PHLX Gold/Silver Sector Index (^XAU) | * PHLX Gold/Silver Sector Index (^XAU) | ||
| − | Data source: [https://finance.yahoo.com/] | + | Data source: [https://finance.yahoo.com/ Yahoo Finance] |
== Contact == | == Contact == | ||
| − | * [ | + | * [https://www.linkedin.com/in/joergosterrieder/ Prof. Dr. Jörg Osterrieder] |
* [mailto:kraehmik@students.zhaw.ch Mike Krähenbühl] | * [mailto:kraehmik@students.zhaw.ch Mike Krähenbühl] | ||
Latest revision as of 09:46, 27 August 2022
Details
- Authors: Mike Krähenbühl
- Title: The efficient market hypothesis for Bitcoin in the context of neural networks
- Supervisior: Prof. Dr. Jörg Osterrieder
- Degree: Bachelor of Science
- University: Zurich University of Applied Sciences
- Year: 2022
- Status: Working Paper
Summary
Examining if additional input features in a feedforward neural network improve the prediction accuracy for daily Bitcoin price movements and if the Bitcoin market is efficient as per the weak form of the efficient market hypothesis.
Abstract
This study examines the weak form of the efficient market hypothesis for Bitcoin using a feedforward neural network. Due to the increasing popularity of cryptocurrencies in recent years, the question has arisen, as to whether market inefficiencies could be exploited in Bitcoin. Several studies we refer to here discuss this topic in the context of Bitcoin using either statistical tests or machine learning methods, mostly relying exclusively on data from Bitcoin itself. Results regarding market efficiency vary from study to study. In this study, however, the focus is on applying various asset-related input features in a neural network. The aim is to investigate whether the prediction accuracy improves when adding equity stock indices (S&P 500, Russell 2000), currencies (EURUSD), 10 Year US Treasury Note Yield as well as Gold&Silver producers index (XAU), in addition to using Bitcoin returns as input feature. As expected, the results show that more features lead to higher training performance from 54.6% prediction accuracy with one feature to 61% with six features. On the test set, we observe that with our neural network methodology, adding additional asset classes, no increase in prediction accuracy is achieved. One feature set is able to partially outperform a buy-and-hold strategy, but the performance drops again as soon as another feature is added. This leads us to the partial conclusion that weak market inefficiencies for Bitcoin cannot be detected using neural networks and the given asset classes as input. Therefore, based on this study, we find evidence that the Bitcoin market is efficient in the sense of the efficient market hypothesis during the sample period. We encourage further research in this area, as much depends on the sample period chosen, the input features, the model architecture, and the hyperparameters.
Important links
Data
- Bitcoin (BTC-USD)
- S&P 500 (ˆGSPC)
- Russell 2000 (ˆRUT)
- EUR/USD (EURUSD=X)
- 10 Year Treasury Note Yield (^TNX)
- PHLX Gold/Silver Sector Index (^XAU)
Data source: Yahoo Finance