Order flow analysis of cryptocurrency markets

Silantyev, Eduard

doi:10.1007/s42521-019-00007-w

Cited by 14 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, sales and wallets were chosen as proxies for economic significance and activity of NFTs. The results suggest that these are appropriate metrics, which also suggests the use of similar metrics in other blockchain-specific articles, e.g., [27][28][29]). Nevertheless, it must be noted that there are a variety of other NFT-specific metrics whose inclusion could lead to differentiated or different results.…”

Section: Discussionmentioning

confidence: 61%

The Non-Fungible Token (NFT) Market and Its Relationship with Bitcoin and Ethereum

Ante¹

2022

FinTech

169

View full text Add to dashboard Cite

Non-fungible tokens (NFTs) are transferrable rights to digital assets, such as art, in-game items, collectables, or music. The phenomenon and its markets have grown significantly since early 2021. We investigate the interrelationships between NFT sales, NFT users (unique active blockchain wallets), and the pricing of Bitcoin (BTC) and Ether (ETH). Using daily data between January 2018 and April 2021, we show that a Bitcoin price shock triggers an increase in NFT sales. Also, Ether price shocks reduce the number of active NFT wallets. The results suggest that (larger) cryptocurrency markets affect the growth and development of the (smaller) NFT market, but there is no reverse effect.

show abstract

Section: Discussionmentioning

confidence: 61%

The Non-Fungible Token (NFT) Market and Its Relationship with Bitcoin and Ethereum

Ante¹

2022

FinTech

169

View full text Add to dashboard Cite

show abstract

“…Goldstein et al [8] show that HFTs on the Australian Securities Exchange take advantage of this predictability. Silantyev [9] conducts an in-depth analysis on the trade and quote data of the XBTUSD perpetual contract and demonstrates that the trade flow imbalance is better at explaining contemporaneous price changes than the aggregate order flow imbalance. Niu et al [10] studied the valuation of vulnerable European options incorporating the reduced-form approach, which models the credit default of the counterparty.…”

Section: Related Work Of Tradingmentioning

confidence: 99%

“…p values, R-squared, and coefficients of c i estimated by model(9) for averaging 50 stocks in March 2019.…”

mentioning

confidence: 99%

The Price Impact of Order Book Events from a Dimension of Time

Chi

Zhao

Huang

2021

Scientific Programming

View full text Add to dashboard Cite

We propose a new linear model to explain the price move by Level-2 high-frequency data in Chinese mainland stock market. In Chinese stock market, the cancellation ratio is very low, and imbalanced order flow prevails most of the time in the trading periods. From time dimension viewpoint, we find the difference of efficiency of limit orders executed, respectively, in bid/ask limit order book, order execution imbalance (OEI), could improve the classic model of Cont et al. (2014) based on market microstructure of Chinese mainland stock market. In particular, when market’s liquidity is booming, our model’s explanatory power and R-squared increased sharply. And the correlations of OEI are very high that may be exploited to predict the price move in the next time window for doing high-frequency trading.

show abstract

“…The Limit-Order Books of cryptocurrency markets share many common characteristics with those of traditional markets, especially at the microstructure level. The main difference is due to the lower average depth of the book in cryptocurrency markets; this leads to other differences related to the way the order book absorbs order flows and trade flow imbalances (Silantyev 2019).…”

Section: Introductionmentioning

confidence: 99%

Ascertaining price formation in cryptocurrency markets with machine learning

Fang

Chung

Ventre

et al. 2021

The European Journal of Finance

View full text Add to dashboard Cite

The cryptocurrency market is amongst the fastest-growing of all the financial markets in the world. Unlike traditional markets, such as equities, foreign exchange and commodities, cryptocurrency market is considered to have larger volatility and illiquidity. This paper is inspired by the recent success of using machine learning for stock market prediction. In this work, we analyze and present the characteristics of the cryptocurrency market in a high-frequency setting. In particular, we applied a machine learning approach to predict the direction of the mid-price changes on the upcoming tick. We show that there are universal features amongst cryptocurrencies which lead to models outperforming asset-specific ones. We also show that there is little point in feeding machine learning models with long sequences of data points; predictions do not improve. Furthermore, we solve the technical challenge to design a lean predictor, which performs well on live data downloaded from crypto exchanges. A novel retraining method is defined and adopted towards this end. Finally, the trade-off between model accuracy and frequency of training is analyzed in the context of multi-label prediction. Overall, we demonstrate that promising results are possible for cryptocurrencies on live data, by achieving a consistent 78% accuracy on the prediction of the mid-price movement on live exchange rate of Bitcoins vs. US dollars.

show abstract

Order flow analysis of cryptocurrency markets

Cited by 14 publications

References 34 publications

The Non-Fungible Token (NFT) Market and Its Relationship with Bitcoin and Ethereum

The Non-Fungible Token (NFT) Market and Its Relationship with Bitcoin and Ethereum

The Price Impact of Order Book Events from a Dimension of Time

Ascertaining price formation in cryptocurrency markets with machine learning

Contact Info

Product

Resources

About