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.

Phase 1 establishes the ground truth about every wallet the system observes. It answers a single question: given everything this wallet has ever done on Pump.fun, how good are they? The answer is a 0–100 alpha score computed from seven independently-weighted components. This score is the most important single input to the ML models — a strong wallet buy on a new token is the foundation of every high-confidence signal.

Overview

FeatureComputer

Runs every 30 minutes. Computes a comprehensive behavioural feature set for up to 5,000 recently active wallets and writes results to wallet_features.

WalletScorer

Runs every 30 minutes. Reads updated features and produces a 0–100 alpha score with a confidence value scaled by trade count.

PnlCalculator

Pairs buy and sell events per wallet per token using FIFO matching to compute realised P&L, hold time, and win/loss status.

PeakTracker

Retrospectively measures price peaks at 1h, 4h, and 24h after a signal, producing the ground-truth labels used for ML training.

FeatureComputer

The FeatureComputer runs every 30 minutes and processes up to 5,000 wallets that have been active in the last 35 minutes, or that have never had features computed and have bought at least 3 tokens. Features are computed with point-in-time correctness — they reflect only what was known at the time of observation, not retroactively adjusted data.
How quickly and how early a wallet enters relative to a token’s launch:
FeatureDescription
avg_seconds_after_creationAverage time between token launch and this wallet’s buy
pct_buys_under_60sShare of buys placed within 60 seconds of token launch
pct_buys_under_300sShare of buys placed within 5 minutes of token launch
pct_top10_entriesHow often this wallet is among the first 10 buyers
The distribution of how much SOL this wallet deploys per trade:
FeatureDescription
avg_sol_per_buyMean buy size in SOL
median_sol_per_buyMedian buy size (robust to outliers)
sol_size_stddevStandard deviation of buy size
max_single_buyLargest single buy ever recorded
How long wallets hold positions, and whether they flip or hold:
FeatureDescription
avg_hold_time_secondsAverage time between buy and sell across all positions
pct_quick_flipsShare of positions exited within 5 minutes
pct_diamond_handsShare of positions held longer than 24 hours
Which creators a wallet trades, and how concentrated their activity is:
FeatureDescription
unique_creators_tradedNumber of distinct creators this wallet has bought from
pct_repeat_creator_buysShare of buys on tokens from creators they’ve traded before — can indicate insider relationships
Recent activity frequency and realised performance metrics:
FeatureDescription
active_days_30dNumber of distinct days active in the last 30 days
tokens_tradedTotal unique tokens bought
graduation_rateShare of tokens bought that eventually graduated
win_rateShare of positions closed in profit
sol_weighted_returnReturn weighted by SOL deployed
avg_realized_multipleAverage realised return multiple
avg_peak_multipleAverage peak available return multiple
capture_efficiencyRatio of realised return to peak available return
profit_factorGross profit divided by gross loss
return_stddevStandard deviation of per-position returns

WalletScorer

The WalletScorer runs every 30 minutes on wallets whose features have been updated since their last scoring. It requires at least 10 traded tokens to produce a valid score. The resulting alpha score runs from 0 to 100 and is computed from seven independently-weighted components:
ComponentWeightDescription
Graduation rate20%Share of tokens bought that eventually graduated to Raydium. Normalised against a 50% ceiling.
Win rate20%Share of positions closed in profit.
Capture efficiency15%How much of the available peak return the wallet actually captured. A wallet that always sells near the top scores highly.
Return consistency15%Inverse of return standard deviation. High variance hurts the score.
Buy rank10%How early the wallet typically enters relative to other buyers. Earlier entry = higher score.
Recency10%Exponential decay: wallets inactive for 14+ days lose score progressively.
Discovery10%Average peak multiple of tokens bought. Rewards wallets that find tokens before the crowd.
Wallets classified as bots are capped at a maximum alpha score of 30, regardless of their performance metrics. A bot that wins frequently is not a useful signal source.
The confidence value (0–1) scales with the number of tokens traded, reaching full confidence at 50 tokens. A high-scoring wallet with only 12 trades carries less weight than one with 80.

PeakTracker

The PeakTracker retrospectively measures the highest price multiples reached by tokens after a signal was emitted. It runs continuously and updates each signal with observed outcomes:
LabelDescription
peak_multiple_1hHighest price multiple within 1 hour of the signal
peak_multiple_4hHighest price multiple within 4 hours
peak_multiple_24hHighest price multiple within 24 hours
reached_2x_1hBinary: did the token reach 2× within 1 hour?
reached_3x_30mBinary: did the token reach 3× within 30 minutes?
These are the ground-truth labels that the ML models in Phase 3 are trained against. Without accurate peak tracking, the model cannot learn which signals actually resulted in profitable outcomes.

PnlCalculator

The PnlCalculator pairs buy and sell events per wallet per token to compute realised P&L. It uses FIFO matching — the oldest open buy is matched against each sell — and records:
  • Realised multiple per position
  • Hold time in seconds
  • Whether the position was a win or a loss
These outputs feed directly into FeatureComputer (to populate return metrics) and into WalletScorer (to compute win rate, profit factor, and related components).

OutcomeTracker

The OutcomeTracker closes the feedback loop for signal quality. Every signal is checked against actual on-chain outcomes at three checkpoints:
1h  → updates peak_multiple_1h, reached_2x_1h
4h  → updates peak_multiple_4h
24h → updates peak_multiple_24h, final outcome classification
This data feeds PeakTracker, ML model training pipelines, and the ModelMonitor in Phase 3. It is the mechanism that connects real-world outcomes back to the features that predicted them.

Build docs developers (and LLMs) love