**[Disclaimer]** There have only been a handful of games played for each team which limits the amount and quality of stats (and these are stat based projections). This makes the first month of projections WILD. Best of luck!

These are statistical projections and shouldn’t be the only thing that factors in to betting on a team, the stats only tell part of the story. Keep an eye on injuries, COVID Issues, and players returning from injury.

Like what you see? Please subscribe or follow me on Twitter (@AnalyticsB2) for the latest news and post info. Want to support the statistical data or have suggestions for improvement, feel free to send me an email (B2SportsStats@gmail.com) or you can donate via the website, Venmo (@B2stats) or Cashapp ($B2stats).

**Next Project:** Projections for MLB DFS. Look for periodic updates via twitter. I’m shooting for a mid May release.

NOTE: The code that pulls Vegas game lines, may not be able to distinguish the double headers so the two listed lines may be the same and subsequently wrong for 1 of the games (Pulls the data based on team name).

All double headers are accounted for being 7 innings.

## Summary of Projections

#### Model Record

#### Model Rank

#### Consensus Record

#### Consensus Profitability

#### Model Consensus

## Sharp Report

ML – Some Sharp Action has come in on the Indians, Orioles, Rays, & Rangers.

O/U – Some Sharp action has come in on the Royals/Tigers Under 8.5 & Phillies/Cardinals Under 8.

## Bet Ratings

**[Disclaimer]** This is the first attempt at doing something like this, it is largely unproven, and it has had little testing, use the data at your own risk.

Welcome to the new and hopefully awesome bet rating system I came up with. I have been working on this for a while and I hope it is useful. So far through 2 days of trial the system has went 2-3, so I made some tweaks, and yesterday went 4-,1 so jury is still out on if this works or not. It’s still early in the season and some teams haven’t played many home/away games or been favored/underdogs, etc. so even if it starts out poorly I plan on only making small tweaks and playing this out for a while to see where it normalizes.

The idea behind this is to take into account the statistical projections from the top rated model (in this case SVM) along with other things the model doesn’t account for to try to give each side/total a rating (or grade). I tried to include everything I look at before making my own bets, including some additional things, to develop a custom grading system. This process takes the top models projection probabilities, each sides betting value, which side the Sharp action is on (if any), records & trends after a day off/home vs away/day vs night game/as a fav vs as a dog/high vs low O/U totals/coming off a win or loss, the average runs scored per win vs projected runs today, and lastly significant injuries (Pulled from the IL so doesn’t account for just a day off. Injury rating determined by a players RAR). Each of these factors receives weights to produce an overall “Rating.” Everything else like last 10 games, starting pitchers, bullpens, team stats (traditional and advanced), & even home vs away is accounted for in the stats models.

Then I publish the 5 highest rated sides/totals, not the ones with “good” Ratings (I don’t know what score constitutes a good vs bad rating… yet).

Rating Scale: Theoretically, the scale is 0-200… realistically its probably about 0-100. These are all based on probabilities and expected win % from the various data and previous outcomes, and multiplying probabilities reduces the numbers drastically. In simple terms, if 2 events each have a 50% chance of happening, then the odds both happen is 25%, so in order for the scale to reach its max of 200, there has to be a 100% probability of each factor happening.

How to read the charts below: “Best Bets” are simply the highest rated side/total for that type of bet. “Matchups” is simply the difference between each sides rating. For example, SEA has the highest rating for today’s ML picks at ~59, but they are 3rd in Matchups. That means that their opponent is also rated higher than others opponents and the difference between SEA and their opponent is about 29 points. Meanwhile, ATL is not on the “Best Bets” so their rating isn’t one of the top 5 for today’s games, but the difference between them and their opponent is the highest for todays games. O/U Matchups is simply the difference in the “Over” Grade vs the “Under” grade.

Hopefully that all makes sense, if not please leave a comment here so I can answer them and everybody else can see the responses.

If you have any feedback or suggestions, please let me know. I have never even attempted something like this so any idea’s or feedback are greatly appreciated.

#### Record

#### Moneyline

#### ATS

#### Over/Under

# Model Projections

## 1. SVM

#### Model Projections

How to read the projections: The model type is at the very top. Matchups are denoted by the alternating white/green pairings, away teams are on top, home teams on bottom. The model analyzes the matchup and projects the home and away teams score (Proj Score). The difference between the home teams score and the away teams score give us what the model says the line should be (Proj Line). The “Line” column is what the Vegas line is at the time I run the model. The “Line Diff” is the difference in the projected line and the Vegas line. A positive line diff means the projected line is in the away teams favor compared to the Vegas line, negative means the projected line is in the home teams favor. The “Cover Prob” uses a normal distribution and the teams variance to project each teams probability to cover the listed Vegas line. Same thing for totals, “Proj Total” is the sum of the projected scores, “Line Total” is the listed Vegas total for the game, the difference between the two, and the probability to go over or stay under denoted by “O” and “U”.

*Added first 5 inning projections.

#### Betting edge

If you don’t understand what you are looking at, I recommend reading my post about betting tips. The percentages show the betting Edge, which is the cover prob (from above) minus the implied probability (-110 odds implied prob is 52.4%). If a team has a 92.4% chance to win and a 52.4% implied probability (or -110 odds), the Edge is 40%. The Edge alone doesn’t mean you should blindly bet it. To quantify, >35% is great value, 20-35% is really good, 10-20% is decent, <10 is ok value, blanks are negative value. ML is moneyline.

## 2. Adaptive Boosting (Ada Boost)

#### New Model Projections

How to read the projections: The model type is at the very top. Matchups are denoted by the alternating white/green pairings, away teams are on top, home teams on bottom. The model analyzes the matchup and projects the home and away teams score (Proj Score). The difference between the home teams score and the away teams score give us what the model says the line should be (Proj Line). The “Line” column is what the Vegas line is at the time I run the model. The “Line Diff” is the difference in the projected line and the Vegas line. A positive line diff means the projected line is in the away teams favor compared to the Vegas line, negative means the projected line is in the home teams favor. The “Cover Prob” uses a normal distribution and the teams variance to project each teams probability to cover the listed Vegas line. Same thing for totals, “Proj Total” is the sum of the projected scores, “Line Total” is the listed Vegas total for the game, the difference between the two, and the probability to go over or stay under denoted by “O” and “U”.

*Added first 5 inning projections.

#### Betting Edge

If you don’t understand what you are looking at, I recommend reading my post about betting tips. The percentages show the betting Edge, which is the cover prob (from above) minus the implied probability (-110 odds implied prob is 52.4%). If a team has a 92.4% chance to win and a 52.4% implied probability (or -110 odds), the Edge is 40%. The Edge alone doesn’t mean you should blindly bet it. To quantify, >35% is great value, 20-35% is really good, 10-20% is decent, <10 is ok value, blanks are negative value. ML is moneyline.

Do you do player vs player matchup stats for these projections? Or team stats?

For baseball its sort of both. So it takes each starting pitchers stats vs the team batting. It projects the starting pitchers estimated length into the game they will go and then uses the bullpens stats (team) vs the team batting for the remainder of the game (so if it projects a starter to throw 5 innings then it would be the starter vs the batters for 5 innings, and the bullpen vs the batters for the other 4).