Detect Crypto Liquidity Shocks

Detect Crypto Liquidity Shocks

This workflow continuously gathers and analyzes multiple layers of crypto market data to detect unusual liquidity shocks and whale activity in real-time. It combines orderbook details, on-chain flows, market prices, snapshot data, and AI-driven whale tracking to generate comprehensive alerts for traders or risk analysts.

It performs the following key actions:

1. Fetches live orderbook data from Binance to assess market microstructure.
2. Retrieves on-chain exchange flow metrics from CryptoQuant to monitor asset movements.
3. Collects real-time pricing and market stats from CoinGecko.
4. Gets additional snapshot data from Massive for broader market insights.
5. Performs an AI-powered internet search for recent whale tracking intelligence from specialized sources.
6. Normalizes and merges all collected data, applying AI analysis to score and flag anomalies based on defined risk dimensions.

What You Need

You will need a few API keys to power the different data feeds in this workflow:

How the Flow Works

1. Binance Orderbook Fetch: Utilizes the Binance API to pull the current orderbook depth for a specified symbol and limit, evaluating the spread, depth, and bid/ask imbalances.
2. CryptoQuant Exchange Flows Fetch: Gets net inflow and outflow data of Bitcoin across exchanges over a selected time window to detect abnormal exchange movements.
3. CoinGecko Market Data Fetch: Fetches the latest price, 24-hour changes, volume, and market cap for the coin to track market trends.
4. Massive Snapshot Fetch: Retrieves snapshot ticker data to gain additional market status context.
5. AI Whale Tracking Search: Runs an AI-powered internet search focusing on whale activities like large wallet movements, smart money flows, and exchange-related influxes over the last few hours.
6. Data Merge and Normalization Node: Combines outputs from all previous data sources into a structured object, gracefully handling any missing or faulty inputs.
7. AI Analytical Scoring: Processes the merged data with a quantitative risk analyst prompt to detect and score anomalies. It uses thresholds like spread norms, depth, exchange flow surges, price changes, and whale activity presence to determine risk.
8. Email Alert Generation: Sends a structured, color-coded alert report directly to your inbox with composite scores and specific trading recommendations.

Output

At the end of the run, you get a detailed email report summarizing:

1. Orderbook health indicators including spread and depth metrics.
2. On-chain exchange flow surges flagged for abnormality.
3. Market price trends and volume changes.
4. Whale intelligence flags based on recent large transactions or accumulation patterns.
5. A consolidated anomaly score with explanations and risk flags to trigger alerts or further investigation.

Notes

1. Keep your API keys secure and never expose them in public environments.
2. The thresholds for anomalies in the AI scoring logic can be adjusted based on your personal risk appetite or current market conditions.
3. The AI whale tracking relies on web search results, meaning its coverage and response completeness may vary depending on available public information.
4. Run periodic tests to verify connectivity with each data source, as any API downtime could affect the accuracy of your alerts.