Predictive Analytics for Roster Update Gems!
-
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamondBonus deep cut upgrade potential:
Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
-
Appreciate the work you have done. But do you know when they upgrade players? Is it like every week or two weeks?
-
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
-
@trex-mlx_xbl said in Predictive Analytics for Roster Update Gems!:
Appreciate the work you have done. But do you know when they upgrade players? Is it like every week or two weeks?
Bi-Weekly. Next round will come out 5/14. My numbers usually get more accurate the closer we get, but it's already led me to a few big hits on the first round.
-
@trex-mlx_xbl said in Predictive Analytics for Roster Update Gems!:
Appreciate the work you have done. But do you know when they upgrade players? Is it like every week or two weeks?
i believe its every other friday at 3:00 pm/ theres a roster update every week but very minimal overall changes
-
@trex-mlx_xbl said in Predictive Analytics for Roster Update Gems!:
Appreciate the work you have done. But do you know when they upgrade players? Is it like every week or two weeks?
Every two weeks I believe so next Friday is when the next round drops.
-
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
Rich Rod is a 93% to gold on the model but we know that Pirates players rarely see the love. I haven't invested as his price has been up already and I found a few better options for this run but he's dealing game in game out up there.
As far as J.D., I question whether the hitting stats will boost enough to get him to diamond with the questionable fielding and physicals. He'd need to get into the high 90's against righties for C+P and keep destroying lefties to do it. Not impossible by any means.
-
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
Rich Rod is a 93% to gold on the model but we know that Pirates players rarely see the love. I haven't invested as his price has been up already and I found a few better options for this run but he's dealing game in game out up there.
Honestly, I bought him as a diamond longshot. His stats have been pretty good in general the last two years but this year he is the most dominant reliever so far.
Honestly not sure how Matt Barnes got a POTM card over him. I also like bryan Reynolds as a longer term option....obviously I’m a pirates fan lol.
-
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
Rich Rod is a 93% to gold on the model but we know that Pirates players rarely see the love. I haven't invested as his price has been up already and I found a few better options for this run but he's dealing game in game out up there.
As far as J.D., I question whether the hitting stats will boost enough to get him to diamond with the questionable fielding and physicals. He'd need to get into the high 90's against righties for C+P and keep destroying lefties to do it. Not impossible by any means.
I mean, his inside edge boosts make him a diamond almost every game...I believe yesterday he played as an 86.
I believe he was diamond two years ago right? Plus we’ve seen SDS mess with defensive stars before to push someone over.
-
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
Rich Rod is a 93% to gold on the model but we know that Pirates players rarely see the love. I haven't invested as his price has been up already and I found a few better options for this run but he's dealing game in game out up there.
As far as J.D., I question whether the hitting stats will boost enough to get him to diamond with the questionable fielding and physicals. He'd need to get into the high 90's against righties for C+P and keep destroying lefties to do it. Not impossible by any means.
I mean, his inside edge boosts make him a diamond almost every game...I believe yesterday he played as an 86.
I believe he was diamond two years ago right? Plus we’ve seen SDS mess with defensive stars before to push someone over.
inside edge doesnt really mean anything relative to the players actual stats
-
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
Rich Rod is a 93% to gold on the model but we know that Pirates players rarely see the love. I haven't invested as his price has been up already and I found a few better options for this run but he's dealing game in game out up there.
As far as J.D., I question whether the hitting stats will boost enough to get him to diamond with the questionable fielding and physicals. He'd need to get into the high 90's against righties for C+P and keep destroying lefties to do it. Not impossible by any means.
I mean, his inside edge boosts make him a diamond almost every game...I believe yesterday he played as an 86.
I believe he was diamond two years ago right? Plus we’ve seen SDS mess with defensive stars before to push someone over.
Yes he was. At the end of the day SDS is going to do whatever they're going to do. I invest based on my model and don't take IE into account as the stat bonuses seem to disagree with each other often.
For example, based on my model the same stat increases given to him would only bring him to an 84 where if you give him one point in durability he's an 85. It'll be close!
-
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
At what point do they look at JDs hitting stats and be like.. he's hitting how his ratings say he should be hitting.
-
What do you have on Framill Reyes going gold
-
@louieepthree_psn said in Predictive Analytics for Roster Update Gems!:
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
At what point do they look at JDs hitting stats and be like.. he's hitting how his ratings say he should be hitting.
I think there is an argument he should be where he was at in 19 which was an 85 overall. I think it was somewhat absurd they dropped him to an 81 to begin with if they truly use three years And weighted less than half a season so much last year.
-
@chuckclc_psn said in Predictive Analytics for Roster Update Gems!:
What do you have on Framill Reyes going gold
He's been hanging around in the 50's for a few weeks now without a lot of change. The speed and fielding, similarly to J.D., limit him pretty bad. Unless we see a big jump in average and that power sticks around over a bigger sample, I don't think it's looking good for him.
-
xander has gotta be going diamond before kris bryant and jd and especially stanton
-
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@louieepthree_psn said in Predictive Analytics for Roster Update Gems!:
@locutusofburg said in Predictive Analytics for Roster Update Gems!:
@anoraka_psn said in Predictive Analytics for Roster Update Gems!:
Hello everybody, I've been running a predictive analytics model since '20 now to identify rating changes of players as well as an accompanying model that predicts increases/decreases in overall based on those rating changes. Last year I was sitting at a .7 r^2 for accuracy of updates and I'm constantly looking to refine my model.
It pulls in players' real-life stats over the past 3 seasons and compares them with samples of players who have been upgraded/downgraded per rating category, so theoretically the longer it runs and the more data I feed to it, the more accurate it will be.
Here's a few guys that it has getting upgraded, along with a % probability that they're heading upwards:
Kris Bryant - 88% probability to diamond
J.D. Martinez - 74% probability to diamond
Xander Bogaerts - 73% probability to diamond
Giancarlo Stanton - 84% probability to diamond
Vlad Jr. - 71% probability to diamond
Bonus deep cut upgrade potential:Christian Javier, based on my model, has a 94% chance of going gold and a 63% chance of going diamond.
What’s your analysis on Richard Rodriguez going gold?
JD Martinez..I bought into him already. Got 85 of him under 2k. Even with the horrendous defense those hitting stats just HAVE to continue to be boosted.
At what point do they look at JDs hitting stats and be like.. he's hitting how his ratings say he should be hitting.
I think there is an argument he should be where he was at in 19 which was an 85 overall. I think it was somewhat absurd they dropped him to an 81 to begin with if they truly use three years And weighted less than half a season so much last year.
I absolutely think he should be a diamond. I don't think the bat is at all the problem for him.
-
@zombiekills-128_xbl said in Predictive Analytics for Roster Update Gems!:
xander has gotta be going diamond before kris bryant and jd and especially stanton
I think that out of those 5 Bryant, Xander and Stanton have the best chance at an upgrade. The thing with Bryant is that his fielding is already elite so any increase in hitting stats will balloon his rating very quickly compared to an equal increase in hitting stats for Xander.
-
It’s honestly dumb Xander wasn’t diamond to start the year.
-
@zombiekills-128_xbl said in Predictive Analytics for Roster Update Gems!:
xander has gotta be going diamond before kris bryant and jd and especially stanton
Problem for me is I doubt they would move two people on the same team diamond at the same time...which stinks because honestly both should flip to diamond on the Red Sox.
