01 · What arrives
Risk, drift, and the words come back together.
The platform sends the portfolio composition. The service reads it and does not touch the assets. The answer is three parts: a risk measure, how far the weights have moved from the ones chosen, and an explanation in plain language.
02 · What it does
It watches the book and does not trade it.
- Portfolio analysis Measures how far the weights have moved from the ones chosen, and sets out a rebalance. It does not execute. The holder of the portfolio decides.
- Many portfolios Flags only the portfolios where something changed: risk, distance from the chosen weights, or a depeg. It does not repeat the same alert. A stablecoin with no peg reading is not treated as sound.
- Plain language The explanation uses only the numbers the engine calculated. It does not forecast.
- Crypto exposure by market phase Recommended crypto exposure for the current market phase, with the limits the engine states. The holder decides.
03 · What it guarantees
Read-only. The engine counts. Portfolios are not kept.
No keys
Read-only. No private keys, wallets, or exchange credentials.
Engine counts
Deterministic code computes the numbers. Language models only explain them.
Not stored
Client portfolios are not stored. The service analyses them and returns the report.
04 · Not yet
Reports come back with the call. They are not archived.
Produced reports are not stored. On-chain data is not part of the reading yet.
05 · Research
Published methods sit under the numbers.
The engine applies methods published in academic journals.
- Crypto risk factors Liu, Y., Tsyvinski, A. & Wu, X. (2022). Common risk factors in cryptocurrency. The Journal of Finance, 77(2), 1133–1177. https://doi.org/10.1111/jofi.13119
- Portfolio construction López de Prado, M. (2016). Building diversified portfolios that outperform out of sample. The Journal of Portfolio Management, 42(4), 59–69. https://doi.org/10.3905/jpm.2016.42.4.059
- Hierarchical risk parity on crypto Burggraf, T. (2021). Beyond risk parity – A machine learning-based hierarchical risk parity approach on cryptocurrencies. Finance Research Letters, 38, 101523. https://doi.org/10.1016/j.frl.2020.101523
- Market phases Giudici, P. & Abu Hashish, I. (2020). A hidden Markov model to detect regime changes in cryptoasset markets. Quality and Reliability Engineering International, 36(6), 2057–2065. https://doi.org/10.1002/qre.2673
Portfolio analysis only. It does not execute, and it is not investment advice.