Forecasting of Bitcoin Illiquidity Using High-Dimensional and Textual Features
Faraz Sasani,
Mohammad Moghareh Dehkordi,
Zahra Ebrahimi,
Hakimeh Dustmohammadloo,
Parisa Bouzari,
Pejman Ebrahimi,
Enikő Lencsés,
Mária Fekete-Farkas
Affiliations
Faraz Sasani
Germany School of Economics and Business, Humboldt University of Berlin, 10117 Berlin, Germany
Mohammad Moghareh Dehkordi
Department of Informatics, TUM School of Computation, Information and Technology Technical University of Munich, 80333 Munich, Germany
Zahra Ebrahimi
Department of Informatics, TUM School of Computation, Information and Technology Technical University of Munich, 80333 Munich, Germany
Hakimeh Dustmohammadloo
Department of Management and Entrepreneurship, Unikl University, Kuala Lumpur 50250, Malaysia
Parisa Bouzari
Doctoral School of Economic and Regional Sciences, Hungarian University of Agriculture and Life Sciences (MATE), 2100 Gödöllő, Hungary
Pejman Ebrahimi
Doctoral School of Economic and Regional Sciences, Hungarian University of Agriculture and Life Sciences (MATE), 2100 Gödöllő, Hungary
Enikő Lencsés
Institute of Agricultural and Food Economics, Hungarian University of Agriculture and Life Sciences (MATE), Páter Károly Street 1, 2100 Gödöllő, Hungary
Mária Fekete-Farkas
Institute of Agricultural and Food Economics, Hungarian University of Agriculture and Life Sciences (MATE), Páter Károly Street 1, 2100 Gödöllő, Hungary
Liquidity is the ease of converting an asset (physical/digital) into cash or another asset without loss and is shown by the relationship between the time scale and the price scale of an investment. This article examines the illiquidity of Bitcoin (BTC). Bitcoin hash rate information was collected at three different time intervals; parallel to these data, textual information related to these intervals was collected from Twitter for each day. Due to the regression nature of illiquidity prediction, approaches based on recurrent networks were suggested. Seven approaches: ANN, SVM, SANN, LSTM, Simple RNN, GRU, and IndRNN, were tested on these data. To evaluate these approaches, three evaluation methods were used: random split (paper), random split (run) and linear split (run). The research results indicate that the IndRNN approach provided better results.
