IJDSBDA International Journal of Data Science and Big Data Analytics 2710-2599 SvedbergOpen ijdsbda-1-1-004 10.51483/IJDSBDA.1.1.2021.55-62 Research Paper Bitcoin economic behavior analysis and policy implications by leveraging deep learning and high-frequency data SiakoulisVasilis 1 * PetropoulosAnastasios 2 LazarisPanagiotis 3 1Bank of Greece, 3 Amerikis, 10250 Athens, Greece, E-mail: vsiakoulis@bankofgreece.gr 2Bank of Greece, 3 Amerikis, 10250 Athens, Greece, E-mail: apetropoulos@bankofgreece.gr 3Bank of Greece, 3 Amerikis, 10250 Athens, Greece, E-mail: plazaris@bankofgreece.gr *Corresponding author: Vasilis Siakoulis, Bank of Greece, 3 Amerikis, 10250 Athens, Greece. E-mail: vsiakoulis@bankofgreece.gr 02 2021 1 1 55 62 Abstract

The recent surge in Bitcoin price performance has attracted significant attention from both the market and academic researchers. This paper constitutes the first principled attempt to determine market risk own-funds requirements for Bitcoin. To this end, we examine price microstructure of the USD per bitcoin, and compare to other financial variables, as a proxy toward classifying Bitcoin into the appropriate risk-class. Using the outcomes of this analysis, we classify and quantify the entailed risk from a market risk minimum capital requirements perspective. To perform the prescribed analysis, we introduce a novel methodological paradigm, which adopts bleeding-edge concepts from the field of Data Science and Machine Learning.

 Keywords Bitcoin Cryptocurrencies Extreme gradient boosting Deep neural networks References BalcilarMehmetElieBouriRanganGuptaDavidRoubaud (2017). Can volume predict Bitcoin returns and volatility? A quantiles-based approach. Economic Modelling. 64, 74–81. BarivieraAurelio F (2017). The inefficiency of Bitcoin revisited: A dynamic approach. Economics Letters. 161, 1–4. CheahEng-TuckJohnFry (2015). Speculative bubbles in Bitcoin markets? An empirical investigation into the fundamental value ofBitcoin. Economics Letters. 130, 32–36. CheahEng-TuckMishraTapasParhiMamataZhangZhuang (2018). Long memory interdependency and inefficiency in Bitcoin markets. Economics Letters. ChenTianqiGuestrinCarlos (2016). XGBoost: A Scalable Tree Boosting System. Proc. ACM KDD. ChoKyunghyunMerrienboerBart vanGulcehreCaglarBahdanauDzmitryBougaresFethiSchwenkHolgerBengioYoshua (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Proc. EMNLP. DemirEnderGozgorGirayLauChi KeungMarcoSamuelA. Vigne (2018). Does economic policy uncertainty predict the Bitcoin returns? An empirical investigation. Finance Research Letters. KatsiampaParaskevi (2017). Volatility estimation for Bitcoin: A comparison of GARCH models. Economics Letters. 158, 3–6 KingmaDiederikSalimansTimWellingMax (2015). Variational dropout and the local reparameterization trick. Proc. NIPS. LahmiriSalimSteliosBekirosAntonioSalvi (2018). Long-range memory, distributional variation and randomness of Bitcoin volatility. Chaos, Solitons & Fractals. 107, 43–48. MacDonellAlec (2014). Popping the Bitcoin bubble: An application of log-periodic power law modeling to digital currency. University of Notre Dame working paper. MosbehHsiniMohamedNidhal MOSBAHI (2016). Stock market liquidity measurement via the Bid-ask spread: Tunis stockmarket. Business and Economic Research, Macrothink Institute, 6(2), 65–78. VinodNairHintonGeoffrey (2010). Rectified linear units improve restricted boltzmann machines. Proc. ICML. PhillipAndrewJenniferChanSheltonPeiris (2018). A new look at Cryptocurrencies. Economics Letters. 163, 6–9. PietersGinaSofiaVivanco (2017). Financial regulations and price inconsistencies across Bitcoin markets. Information Economics and Policy. 39, 1–14. QuadranaMassimoKaratzoglouAlexandrasHidasiBalázsCremonesiPaolo (2017). Personalizing Session- based Recommendations with Hierarchical Recurrent Neural Networks. Proc. ASM RecSys. SeeAbigailLiuPeter J.ManningChristopherD. (2017). Get to the point: Summarization with pointer-generator networks. Proc. ACL. TuZhaopengLuZhengdongLiuYangLiuXiaohuaLiHang (2016). Modeling coverage for neural machine translation. Proc. ACL. UrquhartAndrew (2017). Price clustering in Bitcoin. Economics Letters. 159, 145–148. UrquhartAndrew (2016). The inefficiency of Bitcoin. Economics Letters. 148, 80–82.