How MLB Props Work
Every MLB player prop recommendation is driven by data. We combine DraftKings odds, official MLB game logs, historical hit rates, and machine learning to surface the props with the most value.
Our Data Sources
DraftKings Odds
Real-time player prop lines and odds from DraftKings. We pull every available batter and pitcher prop including hits, total bases, strikeouts, runs, RBIs, and more. Market odds serve as the benchmark for identifying value.
MLB Stats API
Official MLB game logs, player statistics, and roster data. We track every at-bat, plate appearance, and pitching outing to build comprehensive player profiles across the full season.
Historical Game Logs
Detailed box score data for every game. We maintain rolling windows of 5, 10, 15, and 20 game lookback periods to capture both short-term streaks and longer-term performance trends.
Matchup Context
Opponent pitcher/batter splits, home/away performance, park factors, and platoon advantages. Context that turns raw stat lines into actionable prop predictions.
How Hit Rates Are Calculated
A hit rate measures how often a player has cleared a specific prop line in recent games. We calculate it across multiple lookback windows to balance recency with reliability.
Last 5 Games
The most recent 5 games. Captures hot streaks and cold spells. Highly reactive to current form but can be noisy due to small sample size.
Last 10 Games
A balanced window that smooths out single-game variance while still reflecting recent performance. Our primary hit rate metric for most analysis.
Last 15 Games
A broader view that reduces noise further. Useful for identifying sustained trends vs. temporary hot/cold streaks.
Last 20 Games
The widest lookback window. Provides the most stable estimate of a player's true rate for a given prop line. Best for props close to their season average.
Example: If a batter has the line set at Over 1.5 Hits and their last 10 game hit totals were [2, 1, 3, 0, 2, 1, 2, 2, 1, 3], they cleared 1.5 in 7 of 10 games = 70% L10 hit rate. We also track home/away splits to account for park and lineup effects.
How EV Is Computed
Expected Value (EV) compares what we think the true probability of a prop hitting is against what DraftKings odds imply. Positive EV means the prop is priced better than the data suggests.
The Formula
EV = (Hit Rate % - DK Implied %) / DK Implied % x 100DK implied probability is derived from the American odds. For example, -130 odds imply 56.5% probability. If the player's L10 hit rate is 70%, the EV is approximately +24%.
Excellent value. Hit rate significantly exceeds DK pricing.
Strong value. Meaningful gap between hit rate and odds.
Moderate value. Positive expected return over time.
Slight value. Thin margin; best combined with other signals.
The Process
Fetch Today's Props & Odds
We pull every MLB player prop from DraftKings, covering 10+ batter categories (Hits, Total Bases, Runs, RBIs, Home Runs, Stolen Bases, etc.) and 6+ pitcher categories (Strikeouts, Outs, Earned Runs, Hits Allowed, etc.).
Compute Hit Rates from Game Logs
For each prop, we check how often the player has cleared that exact line in their last 5, 10, 15, and 20 games. We also compute home/away splits. This tells us the historical frequency — if a player hit Over 1.5 Hits in 8 of their last 10 games, that's an 80% L10 hit rate.
Calculate Expected Value (EV)
EV compares the hit rate probability to the DraftKings implied probability (derived from the odds). If the L10 hit rate implies 75% but DK odds imply 55%, the EV is +20%. Positive EV means the prop is priced better than the historical rate suggests.
Run ML Model Predictions
Our machine learning model analyzes each prop using historical performance, matchup data, and contextual features. It outputs a probability for each outcome. When the model probability significantly exceeds the DK implied probability, it's flagged as a model pick.
Rank, Grade & Present
Props are ranked by EV and model confidence. The 100% Club highlights perfect L5 hit rates. Cheat sheets organize by category. Model picks surface the highest-value opportunities. Everything is transparent — you see the data behind every recommendation.
Model Picks & Confidence
Model picks are props where our ML model identifies strong positive expected value. Each pick receives a confidence level based on how many signals converge.
Strong convergence of signals: high hit rate across multiple windows (L5, L10, L15), positive EV of 15%+, and ML model agreement. Our highest-conviction picks.
Good signal strength with positive EV of 8-15%. Hit rates are solid in at least two lookback windows. The data supports the pick, but the margin is moderate.
A detectable edge with positive EV under 8%. The data leans in one direction but the signals are weaker or fewer lookback windows agree. Worth monitoring but exercise caution.
Key Features
100% Club
Props where a player has hit Over in all of their last 5 games. Perfect recent form at that line makes these the most compelling at-a-glance plays.
Cheat Sheets
Category-by-category breakdowns with every prop ranked by hit rate and EV. Quick-scan tables for building your daily card across all batter and pitcher categories.
Edge Finder
Identifies props where our model probability exceeds the DraftKings implied probability. The bigger the edge, the more value in the bet. Filter by minimum edge and player type.
Trend Alerts
Automatically flags players on sustained hot streaks. When a player's L10 hit rate exceeds 80% with positive EV, we surface it as a trend worth watching.
Disclaimer
Our analysis is for informational purposes only and does not constitute financial or gambling advice. Past performance and hit rates do not guarantee future results. Sports betting involves risk, and you should only wager what you can afford to lose. Always gamble responsibly.