Predicting the Price Movement of Cryptocurrencies Using Linear Law-based Transformation

Paper: arXiv 2305.04884

Authors: Marcell T. Kurbucz, Péter Pósfay, Antal Jakovác

Abstract

The aim of this paper is to investigate the effect of a novel method called linear law-based feature space transformation (LLT) on the accuracy of intraday price movement prediction of cryptocurrencies. To do this, the 1-minute interval price data of Bitcoin, Ethereum, Binance Coin, and Ripple between 1 January 2019 and 22 October 2022 were collected from the Binance cryptocurrency exchange. Then, 14-hour nonoverlapping time windows were applied to sample the price data. The classification was based on the first 12 hours, and the two classes were determined based on whether the closing price rose or fell after the next 2 hours. These price data were first transformed with the LLT, then they were classified by traditional machine learning algorithms with 10-fold cross-validation. Based on the results, LLT greatly increased the accuracy for all cryptocurrencies, which emphasizes the potential of the LLT algorithm in predicting price movements.

Complexity vs Empirical Score

• Math Complexity: 4.5/10
• Empirical Rigor: 5.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents an interesting application of linear law-based feature transformation to intraday cryptocurrency price prediction across four major coins. While the empirical framework relies on standard machine learning algorithms and 10-fold cross-validation without accounting for transaction costs or realistic execution dynamics, the methodology is clear and moderately novel for high-frequency crypto trading.

Research Flowchart

  flowchart TD
    A[Research Goal: Predict crypto intraday price movement using Linear Law-based Transformation LLT] --> B[Data Collection: 1-min interval data for BTC, ETH, BNB, XRP from Binance 2019-2022]
    B --> C[Data Preprocessing: 14-hr nonoverlapping windows<br/>12-hr features, 2-hr target label: Rise/Fall]
    C --> D[Feature Transformation: Apply Linear Law-based Transformation LLT]
    D --> E[Model Training & Evaluation: Traditional ML algorithms with 10-fold cross-validation]
    E --> F[Key Outcome: LLT significantly improves prediction accuracy across all tested cryptocurrencies]