The market-neutral Retail Flow portfolio is designed to measure and respond to retail investor activity.
By analyzing order book data sourced from exchanges, the strategy identifies assets heavily influenced by retail participation. It then takes systematically contrarian positions, seeking to exploit predictable patterns of overreaction and herding behavior.
Order sizes and types are utilized to differentiate between retail and institutional activity. To quantify trade imbalances on the filtered trades, five distinct techniques are employed, their outputs are normalized and combined in an ensemble approach, without any optimization or parameter fitting.
With balanced long and short exposure, the portfolio minimizes directional risk while monetizing behavioral inefficiencies, offering a unique edge in volatile, sentiment-driven markets.
Its universe consists of the most liquid and actively traded assets, identified on rolling basis - various techniques employed to keep it both stable and relevant, as well as survivorship-bias free.
To balance each asset's risk contribution, positions are scaled according to the inverse of their rolling volatility.
The portfolio is rebalanced daily, at midnight UTC, weights are calculated at 11:55am UTC.
The backtest displayed here assumes fixed 0.5% transaction costs.
Universe
Top 30 Market Capitalization Cryptocurrencies
Constructing a portfolio based on these factors leads to a substantial improvement across all performance metrics, as demonstrated in the table.
This market-neutral portfolio selects assets for inclusion based on their cross-sectional factor rankings, allocating capital to those exhibiting the strongest and weakest signals. It is rebalanced daily, on a continuous basis. There are 0.5% transaction costs applied on each position adjustment.
| Portfolio | Benchmark (BTC) | |
|---|---|---|
-45.7% | -76.6% | |
41.4% | 61% | |
1.33 | 0.98 | |
59.1% | 51.4% | |
0.53 | 0.00 | |
-0.04 | 1.00 |
Using the historical weights endpoint (api/v1/historical-weights) to get the weights for the requested time period and the price endpoint (api/v1/price) to get the price series for each underlying asset.
Get the live weights of the Portfolio to integrate it into your production environment.