Predictive Technology (working version) Week 8

[crusader_of_90]

All - I built a model for the NCAA March Madness last year to predict the winners, and half-time and final scores. Reasoning and history show, bet the under for the first round. Everyone is on the road and everyone is amped up to play tough D. I made money following that model.

I am starting to load in data for the IHSA series and it is bare bones presently, with only regular season results loaded.

I need to collect the following:
To improve the accuracy of score predictions for upcoming Illinois High School football games, here are additional types of data that would be useful:

1. Team Stats:
   • Offensive stats (points per game, yards per game, turnovers).
   • Defensive stats (points allowed per game, sacks, interceptions).
   • Special teams performance (field goals, kick returns).
2. Individual Player Stats:
   • Key player performances (quarterback completions, rushing yards, receiving yards).
   • Injuries or players missing games.
3. Game Location:
   • Home vs. away games, as home-field advantage can affect outcomes.
4. Weather Conditions:
   • Past weather conditions during games and forecast for upcoming games (rain, wind, etc.).
5. Historical Matchups:
   • Previous meetings between teams, including head-to-head results.
6. Team Trends:
   • Recent form (winning streaks, losing streaks).
   • Momentum shifts over the season.
7. Coaching Changes:
   • New coaches or changes in team strategy.
8. Strength of Schedule:
   • Quality of opponents faced in previous weeks.

If you have any of this data, it can help improve predictions. Let me know what data you can provide!

 

[crusader_of_90]

Anyone know where I can collect the requested data? Please provide links if you can.

Since I have maxed out my "free" data analysis this AM and cannot load more or get more back until 5:08 this afternoon, these are the scores predicted so far.

Here are my predictions for some key games of Week 8, based on team performance so far:

Thursday, October 17, 2024​

• Woodlawn (6-0) vs. Harlan (3-3): Woodlawn's unbeaten record makes them the favorite. Prediction: Woodlawn win.
• DuSable (1-6) vs. Back of the Yards (3-4): Back of the Yards should take this one given DuSable's struggles. Prediction: Back of the Yards win.
• Solorio Academy (4-3) vs. Gage Park (2-5): Solorio Academy looks stronger on paper. Prediction: Solorio Academy win.

Friday, October 18, 2024​

• Morgan Park (#6 5A) (6-1) vs. Brooks (2-5): Morgan Park has been dominant and should continue their winning ways. Prediction: Morgan Park win.
• Ridgeview-Lexington (2-5) vs. Shelbyville (5-2): Shelbyville should win comfortably. Prediction: Shelbyville win.
• Forreston (2-5) vs. Du-Pec (6-1): Du-Pec’s strong season gives them the edge. Prediction: Du-Pec win.
• Sullivan (7-0) vs. North Lawndale (6-1): This could be a close game, but Sullivan's perfect record might hold. Prediction: Sullivan win.
• Hillcrest (4-3) vs. Blue Island Eisenhower (4-3): Very even matchup, but Hillcrest may have a slight edge. Prediction: Hillcrest win.
• Addison Trail (6-1) vs. Leyden (4-3): Addison Trail should win. Prediction: Addison Trail win.
• Oak Lawn Richards (#8 6A) (6-1) vs. Evergreen Park (3-4): Richards is too strong. Prediction: Richards win.
• Kankakee (#4 6A) (6-1) vs. Thornton (0-7): Kankakee will dominate. Prediction: Kankakee win.
• Marion (4-3) vs. Carbondale (3-4): Marion should have the upper hand here. Prediction: Marion win.
• Lake Forest (5-2) vs. Libertyville (#5 6A) (7-0): Libertyville’s unbeaten record makes them the favorite. Prediction: Libertyville win.
• Manteno (#5 4A) (7-0) vs. Wilmington (#2 3A) (7-0): This is a highly anticipated matchup, but Wilmington’s experience could give them the edge. Prediction: Wilmington win.
• Oswego (#3 8A) (7-0) vs. Minooka (6-1): Oswego has been impressive all season. Prediction: Oswego win.
• East St Louis (#1 6A) (7-0) vs. Edwardsville (#8 7A) (6-1): East St Louis looks too powerful for most teams this season. Prediction: East St Louis win.
• Geneva (#3 6A) (7-0) vs. St. Charles East (2-5): Geneva will likely remain unbeaten. Prediction: Geneva win.
• Naperville Central (#2 8A) (7-0) vs. Sandburg (5-2): Naperville Central should win, though Sandburg might put up a fight. Prediction: Naperville Central win.

These predictions take into account records and past performance. Let me know if you want predictions for any specific games!

 

[RoaminCatholic]

I'm unsure of one mega-spot for all that info... but I can say the IHSA website would have a lot of that up front at no cost and available at any time. At least as far as streaks, points for, points against, HC tenures, home/away (advantage). Where you'd hit the dark again would be the stats. Stats are tough to come by for every program. Some are better than others as you're well aware of keeping them well to begin with, posting them for the public is even more rare.

I'm not sure how you're going about this but I do presume you're entering all the data yourself. If you'd like help collecting some of that "easy" data to help jump start, I'd be more than willing to help. Simply let me know how you'd prefer it formatted and I can start this week. I always enjoy this kind of stuff. I'm not wizard or guru or even really good at the analytical side of things, but I enjoy the heck out of it. lol

 

[crusader_of_90]

I will be in touch!

 

[Gestalt45]

All - I built a model for the NCAA March Madness last year to predict the winners, and half-time and final scores. Reasoning and history show, bet the under for the first round. Everyone is on the road and everyone is amped up to play tough D. I made money following that model.

I am starting to load in data for the IHSA series and it is bare bones presently, with only regular season results loaded.

I need to collect the following:
To improve the accuracy of score predictions for upcoming Illinois High School football games, here are additional types of data that would be useful:

1. Team Stats:
   • Offensive stats (points per game, yards per game, turnovers).
   • Defensive stats (points allowed per game, sacks, interceptions).
   • Special teams performance (field goals, kick returns).
2. Individual Player Stats:
   • Key player performances (quarterback completions, rushing yards, receiving yards).
   • Injuries or players missing games.
3. Game Location:
   • Home vs. away games, as home-field advantage can affect outcomes.
4. Weather Conditions:
   • Past weather conditions during games and forecast for upcoming games (rain, wind, etc.).
5. Historical Matchups:
   • Previous meetings between teams, including head-to-head results.
6. Team Trends:
   • Recent form (winning streaks, losing streaks).
   • Momentum shifts over the season.
7. Coaching Changes:
   • New coaches or changes in team strategy.
8. Strength of Schedule:
   • Quality of opponents faced in previous weeks.

If you have any of this data, it can help improve predictions. Let me know what data you can provide!

Masseyratings is prob your go to for historical head to heads. They provide every game (within last 25 years or so) that a team has played and their total wins, losses and Margin of Victory. For example here’s the link to Loyola. (244-67 wow!)

Massey Ratings - Loyola Acad HSF Opponents Head-to-Head

head-to-head results by opponent for Loyola Academy in HSF

masseyratings.com

 

[crusader_of_90]

AWESOME!!!!

I will use that@