Behavioral Intelligence for MLB

The decisions behind
the numbers.

A hitter can put up good numbers on bad swings, or take great at-bats for a month with nothing to show for it. SIQX scores the at-bat itself — what he swung at, what he let go, how he handled two strikes — and ranks every player in baseball on it. Then it shows you that score next to his actual production, so you can see where the two disagree.

Built from Statcast pitch-by-pitch data. Ten measures for hitters, nine for pitchers, every qualified player, updated daily.

Follow on X / Twitter Read the Methodology
Today’s Pick
Loading today’s pick…
Live Signals

Where a player’s plate decisions and his production disagree, and by how much. These are gaps as they stand today, not forecasts — a hitter can carry one all season.

▲ Breakout Watch
Yordan Alvarez
HOU · SIQX 66.6 · xwOBA .493
Elite production fully backed by decision quality — not a hot streak. Divergence −57 means the behavioral profile is still slightly ahead of the results.
▼ Regression Alert
James Outman
MIN · SIQX 29.8 · div +63
Results are running ahead of a weak behavioral profile. SIQX 29.8 doesn't support even the current modest output — further decline is the likelier path.
▲ Breakout Watch
Juan Soto
NYM · SIQX 66.7 · xwOBA .422
Plate discipline among the league's best. Divergence −52 means the profile still leads the results — the production is behavioral, with room to climb.
▲ Team Watch
Los Angeles Dodgers
SIQX #1 of 30 · composite 59.9
Most complete profile in MLB. Rotation 53.2, bullpen 65.6 (full-pen PSIQX). Alex Call is the #1 hitter in baseball at 89.8 SIQX.
r = +0.444
SIQX vs xwOBA
qualified PA≥150 · 1,447 hitter-seasons · 2023–2026
r = −0.708
PSIQX v2 vs xwOBA
qualified PA≥150 · 1,496 pitcher-seasons · confirmatory
Live moneyline record
loading…

Ten behavioral components.
One behavioral score.

SIQX v14 scores hitters on ten Statcast behavioral components, each percentile-ranked against all qualified hitters in the current season. Components are selected on behavioral validity only; the scoring and weighting are proprietary.

FIQ
Fastball IQ
Contact quality + out-zone take rate on fastballs. Fastball-specific Statcast query.
DSR
Discipline Score Ratio
BB% / (BB%+K%). Most persistent plate discipline signal across 4 seasons.
CHS
Chase Avoidance
Out-of-zone swing rate (inverted). Higher score = better avoidance of bad pitches.
ZWP
Zone Whiff Avoidance
Whiff rate on in-zone pitches (inverted). Higher score = fewer misses on hittable pitches.
ZCN
Zone Contact Rate
Contact rate on pitches in the strike zone. Consistent contact on strikes.
OCN
Out-Zone Contact
Contact rate on out-of-zone pitches. Behaviorally valid -- reinstated v11.
ZAE
Zone Attack Early
In-zone swing rate in early counts (0-0, 1-0, 0-1, 1-1). Rewards early-count aggression.
ECC
Early Count Chase
Out-zone swing rate in early counts (inverted). Poor early decisions compound.
TSS
Two-Strike Survival
Pitches seen per AB after reaching a 2-strike count. Pure decision quality under pressure.
ACW
Ahead Count Waste
Out-zone swing rate when ahead in count (inverted). Elite hitters don't chase when winning.

Nine behavioral components.
One command score.

PSIQX measures what a pitcher forces hitters to do — not raw stuff. Nine behavioral components, each percentile-ranked against all qualified pitchers in the current season. Components are selected on behavioral validity only; the scoring and weighting are proprietary.

HHI
Hard-Hit Suppression
Suppression of hard contact (inverted). Highest individual predictor across seasons.
OZI
Chase Induced
Out-of-zone swing rate the pitcher generates from hitters.
ZWF
Zone Whiff Forced
Swinging misses forced on pitches inside the strike zone.
ZCF
Zone Contact Prevention
Preventing contact on pitches in the zone (inverted).
OCI
Chase Contact Prevention
Preventing contact when hitters chase out of the zone (inverted).
EZC
Early Zone Command
Zone rate in early counts. Count-split behavioral data.
ECI
Early Chase Induced
Chase rate generated before counts develop. Count-split.
TSP
Two-Strike Put-Away
Strikeout conversion in two-strike counts. Count-split.
AZC
Ahead-Count Command
Zone rate when the pitcher is ahead in the count. Count-split.

Decisions lead outcomes.
SIQX finds the gap.

The same outcome can result from excellent decisions or poor decisions that happened to work. SIQX identifies which is which — before the results correct.

1
Score every qualified hitter and pitcher
SIQX pulls Statcast plate discipline data weekly. All 380+ qualified hitters (10 components) and 400+ pitchers (9 components) are scored and percentile-ranked in the current season pool.
2
Identify behavioral divergence
High SIQX with lagging results = breakout candidate. Low SIQX with strong results = regression risk. The model flags both before the market corrects.
3
Apply to daily behavioral edge picks
Behavioral edge across all components identifies market pricing gaps. Primary validation is win rate vs market-implied probability and EV per pick; CLV is a secondary check. Underdog only.

Built on Statcast.
Validated against results.

Full research paper with component definitions, behavioral-validity audit, bullpen separation methodology, validation framework, limitations, and the live pick record. Pick-model selection logic is proprietary and not published.

SIQX: Situational IQ Index — June 2026 (SIQX v12 · revision in progress)

Working paper covering SIQX v12 (hitters), PSIQX v2 (pitchers), the bullpen model, the validation framework, multi-season validation (2023–2026), and threats to validity. The pick model is described at a high level only — selection logic and thresholds are held privately. Correlations re-derived on 1,447 hitter-seasons and 1,496 pitcher-seasons (PA≥150) after the June 2026 count-split correction.

r=.444
SIQX vs xwOBA (PA≥150)
r=.708
PSIQX v2 vs xwOBA
1,447
Qualified hitter-seasons
↓  Download Methodology PDF

Built by a behavioral
data scientist.

SB
Stephen Bridwell
Sr. Applied Scientist · M.I.D.S., UC Berkeley · Tampa, FL

The same discipline that powers SIQX — identifying signal in behavioral data at scale — is the foundation of my professional work in machine learning systems. SIQX applies that expertise to baseball: measuring not what players do, but how they decide.

Follow the picks

Daily behavioral analysis.
Posted every morning.

Daily pick cards, team analysis, breakout and regression flags, and weekly SIQX reports — all on Twitter.

Follow @SIQXindex →
Get notified

Be first to know when SIQX opens up.

SIQX is still in open validation — every pick is posted publicly, win or lose, and the record is building toward a pre-registered checkpoint. Leave your email and you’ll hear when picks go out by email. No picks are being emailed yet.

No spam, no selling your address, unsubscribe any time. Nothing here is betting advice.