Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/alphaleaks60-maker/solvedocs2/llms.txt

Use this file to discover all available pages before exploring further.

A raw buy event on Pump.fun is noise. That same event, attached to a wallet with a 40% graduation rate, a 0.8 capture efficiency, and a consistent history of top-10 entries, is something else entirely. The wallet intelligence system builds and maintains that context for every wallet the pipeline encounters — turning anonymous on-chain activity into a ranked, scored roster of smart money that continuously informs every trading decision.

​
Wallet Discovery

Wallets enter the tracking system through one of three paths.

Graduation-Based

When a token crosses the 85 SOL graduation threshold, WalletDiscovery processes all buyers. Wallets that bought early and held are promoted to is_active = true status.

Signal-Based

Any wallet that triggers a signal — because it trades alongside an already-tracked wallet — is added to the wallets table for future enrichment.

Manual Seeding

Wallets can be added directly to the tracked_wallets Redis set for immediate attention, bypassing the organic discovery pipeline.

​
Wallet Enrichment

The WalletEnrichment service continuously processes newly discovered wallets, fetching their historical Birdeye data (if available) to bootstrap their feature profiles without waiting for live trades. This means a wallet that was previously active before the pipeline started can arrive in the system with a complete historical record rather than beginning at zero.

​
The Alpha Score

The alpha score (0–100) is a single number summarising a wallet’s historical edge. It is designed to reward the behaviours that actually predict future token success — not raw volume or frequency, but quality of entry, ability to hold to meaningful returns, and consistency over time. 
alpha_score =
  graduation_score   × 0.20   +  // Share of bought tokens that graduated
  win_score          × 0.20   +  // Share of positions closed in profit
  capture_score      × 0.15   +  // Ratio of realised to peak return
  consistency_score  × 0.15   +  // Inverse of return standard deviation
  rank_score         × 0.10   +  // How early the wallet typically enters
  recency_score      × 0.10   +  // Exponential decay for inactive wallets
  discovery_score    × 0.10      // Average peak multiple of tokens bought

Confidence Scaling

Confidence scales from 0 to 1 based on trade count, reaching full confidence at 50 tokens. A wallet with 10 trades and a score of 80 is treated meaningfully differently from one with 200 trades and the same score.

Bot Penalty

Wallets classified as bots are hard-capped at a score of 30, regardless of their apparent metrics. Bots can accumulate impressive-looking stats through volume, but their behaviour carries no signal value.

​
Point-in-Time Correctness

A subtle but important property of the alpha score: it is computed at the time of scoring, using only data available up to that point. When the ML model records wallet_score_at_entry, it captures the score as it was when the signal fired, not the wallet’s current score.
This prevents lookahead bias in model training and ensures that historical backtests reflect what was actually knowable at the time of each trade decision.

​
Alpha Decay

Not all smart money signals age equally. Some wallets move markets — when they buy, price moves within seconds. Others have a longer information half-life where their signal remains valid for minutes or more. The AlphaDecayTracker computes a per-wallet decay curve: the average return achievable if you had bought 1s, 5s, 10s, 30s, 60s, 120s, 300s, or 600s after the wallet’s signal. From this curve, two values are derived:

Alpha Half-Life

The delay at which the expected return drops to 50% of the instant return. Wallets with sub-5-second half-lives are effectively unmatchable manually — useful only for bot execution.

Optimal Follow Delay

The delay that maximises expected return. Buying instantly is not always optimal; wallets with half-lives above 60 seconds are significantly more actionable for human traders.

​
Bot Detection

The BotDetector runs every 30 minutes and classifies wallets across three distinct behavioural patterns.
Bought 20+ distinct tokens within a 2-hour window. This pattern is characteristic of broad sniping bots that buy every new token regardless of quality, with no selectivity or edge.
Bought 10+ tokens in 6 hours with average position below 0.05 SOL and very low size variance (stddev < 0.02 SOL). This pattern matches bots testing wallets or accumulating many tiny positions systematically.
Executed buy-to-sell within 60 seconds on 3 or more tokens in 6 hours. This pattern is common among pump-and-dump participants and short-term snipers who are not providing meaningful signal.
Detected bots are written to the wallets table with their bot_type, added to the known_bots Redis set, and capped at a maximum alpha score of 30. The is_bot field feeds directly into the ML model as a feature.

​
Copy-Trade Graph

The copy-trade detection system maps the directional relationship between wallet pairs. When wallet A consistently buys a token 15 seconds before wallet B, across dozens of tokens, it is likely that B is following A through an alert system or automation. The system resolves which wallet is the originator and which is the follower. Signals from followers are treated with lower confidence than signals from originators — a follower’s buy means someone already paid a higher price before the signal fired.
The three copy-trade classifications — bot_copy, alert_copy, and manual_copy — represent meaningfully different latencies and therefore different implications for signal freshness. bot_copy followers are nearly useless as signal sources; manual_copy followers may still carry meaningful lag-adjusted value.

Build docs developers (and LLMs) love

Get started for freeTalk to us