Multi-Factor Inception Networks for Cryptocurrency Portfolio Trading

Summary

This paper presents Multi-Factor Inception Networks (MFIN), a framework for trading multiple cryptocurrencies using price returns and other frequently updated signals. It motivates adding factors such as network hashrate and search interest to address the limited history available for crypto assets. MFIN extends Deep Inception Networks to process multiple factors and assets together.

The model learns representations from returns and produces portfolio position sizes with the objective of maximizing the Sharpe ratio. The paper compares its results with rule-based momentum and mean-reversion strategies, reporting that MFIN produces a higher-Sharpe, less-correlated strategy that differs from conventional hand-crafted factors. It also reports continued returns in 2022–2023, when the compared strategies and the broader crypto market performed poorly. The excerpt provides no detailed experimental setup, numerical performance measures, or transaction-cost analysis, so it is insufficient to assess robustness or practical trading feasibility.

Key ideas

• MFIN extends Deep Inception Networks to handle multiple assets and factors in one trading framework.
• The approach is motivated by the availability of frequently updated crypto metrics and the short history of many assets.
• The model learns from returns and selects portfolio position sizes to optimize the Sharpe ratio.
• The paper reports that its strategy is less correlated with rule-based momentum and mean-reversion approaches.
• The excerpt claims returns persisted in 2022–2023 but gives no figures or implementation details.

Tags

# Multi-Factor Inception: What to Do with All of These Features?


# Multi-Factor Inception: What to Do with All of These Features?









Cryptocurrency trading represents a nascent field of research, with growing adoption in industry. Aided by its decentralised nature, many metrics describing cryptocurrencies are accessible with a simple Google search and update frequently, usually at least on a daily basis. This presents a promising opportunity for data-driven systematic trading research, where limited historical data can be augmented with additional features, such as hashrate or Google Trends. However, one question naturally arises: how to effectively select and process these features? In this paper, we introduce Multi-Factor Inception Networks (MFIN), an end-to-end framework for systematic trading with multiple assets and factors. MFINs extend Deep Inception Networks (DIN) to operate in a multi-factor context. Similar to DINs, MFIN models automatically learn features from returns data and output position sizes that optimise portfolio Sharpe ratio. Compared to a range of rule-based momentum and reversion strategies, MFINs learn an uncorrelated, higher-Sharpe strategy that is not captured by traditional, hand-crafted factors. In particular, MFIN models continue to achieve consistent returns over the most recent years (2022-2023), where traditional strategies and the wider cryptocurrency market have underperformed.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.