English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This study examines the weak form of the efficient market hypothesis forBitcoin using a feedforward neural network. Due to the increasing popularity ofcryptocurrencies in recent years, the question has arisen, as to whether marketinefficiencies could be exploited in Bitcoin. Several studies we refer to herediscuss this topic in the context of Bitcoin using either statistical tests ormachine learning methods, mostly relying exclusively on data from Bitcoinitself. Results regarding market efficiency vary from study to study. In thisstudy, however, the focus is on applying various asset-related input featuresin a neural network. The aim is to investigate whether the prediction accuracyimproves 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, theresults 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 assetclasses, no increase in prediction accuracy is achieved. One feature set isable to partially outperform a buy-and-hold strategy, but the performance dropsagain as soon as another feature is added. This leads us to the partialconclusion that weak market inefficiencies for Bitcoin cannot be detected usingneural networks and the given asset classes as input. Therefore, based on thisstudy, we find evidence that the Bitcoin market is efficient in the sense ofthe efficient market hypothesis during the sample period. We encourage furtherresearch in this area, as much depends on the sample period chosen, the inputfeatures, the model architecture, and the hyperparameters.

The Efficient Market Hypothesis for Bitcoin in the context of neural networks