Paper: arXiv 2307.01599
Authors: Zhenhan Huang, Fumihide Tanaka
Abstract
On-chain data (metrics) of blockchain networks, akin to company fundamentals, provide crucial and comprehensive insights into the networks. Despite their informative nature, on-chain data have not been utilized in reinforcement learning (RL)-based systems for cryptocurrency (crypto) portfolio management (PM). An intriguing subject is the extent to which the utilization of on-chain data can enhance an RL-based system’s return performance compared to baselines. Therefore, in this study, we propose CryptoRLPM, a novel RL-based system incorporating on-chain data for end-to-end crypto PM. CryptoRLPM consists of five units, spanning from information comprehension to trading order execution. In CryptoRLPM, the on-chain data are tested and specified for each crypto to solve the issue of ineffectiveness of metrics. Moreover, the scalable nature of CryptoRLPM allows changes in the portfolios’ cryptos at any time. Backtesting results on three portfolios indicate that CryptoRLPM outperforms all the baselines in terms of accumulated rate of return (ARR), daily rate of return (DRR), and Sortino ratio (SR). Particularly, when compared to Bitcoin, CryptoRLPM enhances the ARR, DRR, and SR by at least 83.14%, 0.5603%, and 2.1767 respectively.
Complexity vs Empirical Score
- Math Complexity: 3.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper introduces a novel RL-based system incorporating on-chain data for cryptocurrency portfolio management, backed by concrete backtesting results on three portfolios with specific performance metrics (ARR, DRR, Sortino ratio) and a detailed five-unit system architecture. The mathematical complexity is moderate, focusing on feature selection via Pearson correlation and RL framework application without heavy theoretical derivations or advanced formulas.
Research Flowchart
flowchart TD A["Research Goal: Impact of On-Chain Data on RL Crypto Portfolios"] --> B["Data Input: On-Chain Blockchain Metrics"] B --> C["Methodology: CryptoRLPM System<br>5 Units: Info Comprehension to Execution"] C --> D["Key Innovation: Metric Specification & Scalable Portfolio"] D --> E["Computational Process: RL-based Training & Backtesting"] E --> F["Key Findings: Outperformance vs. Baselines"] F --> G["Outcome: Significant Boost in ARR, DRR, and Sortino Ratio"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes CryptoRLPM, a novel reinforcement learning system that incorporates on-chain data for end-to-end cryptocurrency portfolio management.
Source sentence
Therefore, in this study, we propose CryptoRLPM, a novel RL-based system incorporating on-chain data for end-to-end crypto PM.
Assumes 2
- The Efficient Market Hypothesis holds for blockchain crypto valuations, i.e., prices reflect all accessible information including on-chain metrics. market
Source sentence
As per the Efficient Market Hypothesis (EMH) [4], a blockchain’s crypto valuation presumably reflects all accessible information, including on-chain metrics.
- On-chain metrics are effective for each cryptocurrency when tested and specified individually. data
Source sentence
On-chain metrics are tested and specified for each cryptocurrency, overcoming the issue of metric ineffectiveness.
Data
crypto
- Historical price data market-prices public
Source sentence
(DFU) retrieves historical price data and on-chain metrics using Binance REST API and Santiment’s SanAPI (SanAPI Basic Subscription) respectively
- On-chain metrics crypto-onchain commercial
Source sentence
(DFU) retrieves historical price data and on-chain metrics using Binance REST API and Santiment’s SanAPI (SanAPI Basic Subscription) respectively
- CM(training) dataset synthetic unknown
Source sentence
CM(training) from October 2020 to December 2021
- CM(validation) dataset synthetic unknown
Source sentence
CM(validation) from January 2022 to February 2022
- CM(backtesting) dataset synthetic unknown
Source sentence
CM(backtesting) from March 2022 to September 2022
Costs
Unclear
Finds 2
- CryptoRLPM outperforms all baselines across three portfolios, achieving at least an 83.14% improvement in accumulated rate of return, a 0.5603% improvement in daily rate of return, and a 2.1767 improvement in Sortino ratio compared to Bitcoin. performance
Source sentence
CryptoRLPM achieves at least a 83.14% improvement on ARR, a 0.5603% improvement on DRR, and a 2.1767 improvement on SR.
- Backtesting shows CryptoRLPM yields positive ARR, DRR, and SR values for all portfolios, while baseline cryptos produce negative ARR. performance
Source sentence
CryptoRLPM consistently outperforms the baselines across all three portfolios, achieving positive values in terms of ARR, DRR, and SR, while the baselines yield negative values on ARR.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 18 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.