2023-2024 Predictions

[ugarte]

An RPI fan and his computer program's ECAC predictions. https://thefieldhouse.substack.com/p/ecac-2023-24-preview?utm_source=profile&utm_medium=reader2

Cornell is #2, and Harvard is #7 below #4 Princeton.

I appreciate that someone is trying to quantify these things rather than making prediction based on feel, but the fact this model ranks Harvard's returning offense as 12th in the league evidences a clear flaw in its methodology, in my opinion. I would guess the issue is that Harvard's top players last year were SO good that they got all the PP time and played a crazy amount of minutes, especially when Harvard needed a goal. So yeah, nearly all the offensive production came from those players, who are gone now. But that doesn't mean the players who played behind them, and will now take on a larger role, are not good players—it just means they didn't add much offensively last year, because they didn't need to.

And though I wish it were true, I just don't see Cornell as an elite team this season. We could compete for an NCAA spot, but if that happens it is most likely as one of the final at-large bids. We have a ton of freshmen, no one who has played more than two years for Cornell (and no one aside from Seger who has played more than two years of college hockey at all). We are still going up against much older and more experienced teams whenever we play a non-Ivy. I like our trajectory but don't expect us to be elite until the fifth-year eligibility rule finally goes away in a couple seasons.

ursusminor told me he posted this here, and I saw this and wanted to reply.

Harvard's 12th ranked returning offense isn't an opinion; it's a fact. They return 122 points and played 34 games, so they return 3.59 points per game, which is last in the league. It's an entirely objective metric. I disagree that it's a flaw in the methodology and think it's much more of a symptom of the lack of college hockey data available to the public (mainly time on ice).

However, I do agree with your points about PP time and general time on ice. Harvard does have good talent that played lower in the lineup that will likely step up. It's entirely possible they beat the projection, and I'd say they are the likeliest team to do that of the 12. Anyone expecting them to maintain their level of last season is mistaken though. Looking at the roster, the only player I see surpassing 30 points is Joe Miller. None of the players that remain are at the level of Coronato, Farrell, or Laferriere. None of the defensemen are at the level of Thrun even though Ian Moore is very good. Those are the players they have to replace, and Harvard isn't equipped to do it regardless of ice time. The players they have are not that caliber, where they put up big numbers and get an NHL deal following the season (with the exception of Miller and Moore).

Sorry if my post came off as overly critical. I do appreciate people trying to quantify this stuff, as I said. And I enjoyed reading your findings and write-up. I also certainly didn't mean to imply that you were putting your thumb on the scale. I understand these metrics are objective and that Harvard's returning points per game number is what it is.

However, the fact you chose to base offensive ranking entirely (mostly?) off of returning points per game is not objective. While the inputs themselves may be objective metrics, choosing which inputs to use is necessarily subjective. I don't deny that you are limited in your data and maybe this is the best you can do; but it's very clear if you look past this one statistic that Harvard is once again going to be very talented this season. They still have by far the most draft picks in the ECAC, by the far most players who were in the central scouting rankings, etc. These are imperfect metrics, but they're other metrics that you could consider factoring into your analysis.

By the way, how do you measure incoming class rank? I may have missed that, but I didn't see it in your post. Cornell's incoming class consists of five draft picks, which I believe is easily the most in the ECAC, but its incoming class is ranked #7.

Looking only at the bold statement, my response is ... so what? Judge the model at the end of the year, not now. You're obviously free to have and share an opinion but he's not being more or less subjective than you are. You make good points, BL, about the hidden skill of last year's backups and the incoming class for Harvard but that doesn't make you less subjective than sezenack (yet). It's an interesting discussion, and i like hearing people poke at the assumptions underlying a prediction, but have some sense of when you're sharing your own subjective metrics too.

[ugarte]

An RPI fan and his computer program's ECAC predictions. https://thefieldhouse.substack.com/p/ecac-2023-24-preview?utm_source=profile&utm_medium=reader2

Cornell is #2, and Harvard is #7 below #4 Princeton.

I appreciate that someone is trying to quantify these things rather than making prediction based on feel, but the fact this model ranks Harvard's returning offense as 12th in the league evidences a clear flaw in its methodology, in my opinion. I would guess the issue is that Harvard's top players last year were SO good that they got all the PP time and played a crazy amount of minutes, especially when Harvard needed a goal. So yeah, nearly all the offensive production came from those players, who are gone now. But that doesn't mean the players who played behind them, and will now take on a larger role, are not good players—it just means they didn't add much offensively last year, because they didn't need to.

And though I wish it were true, I just don't see Cornell as an elite team this season. We could compete for an NCAA spot, but if that happens it is most likely as one of the final at-large bids. We have a ton of freshmen, no one who has played more than two years for Cornell (and no one aside from Seger who has played more than two years of college hockey at all). We are still going up against much older and more experienced teams whenever we play a non-Ivy. I like our trajectory but don't expect us to be elite until the fifth-year eligibility rule finally goes away in a couple seasons.

ursusminor told me he posted this here, and I saw this and wanted to reply.

Harvard's 12th ranked returning offense isn't an opinion; it's a fact. They return 122 points and played 34 games, so they return 3.59 points per game, which is last in the league. It's an entirely objective metric. I disagree that it's a flaw in the methodology and think it's much more of a symptom of the lack of college hockey data available to the public (mainly time on ice).

However, I do agree with your points about PP time and general time on ice. Harvard does have good talent that played lower in the lineup that will likely step up. It's entirely possible they beat the projection, and I'd say they are the likeliest team to do that of the 12. Anyone expecting them to maintain their level of last season is mistaken though. Looking at the roster, the only player I see surpassing 30 points is Joe Miller. None of the players that remain are at the level of Coronato, Farrell, or Laferriere. None of the defensemen are at the level of Thrun even though Ian Moore is very good. Those are the players they have to replace, and Harvard isn't equipped to do it regardless of ice time. The players they have are not that caliber, where they put up big numbers and get an NHL deal following the season (with the exception of Miller and Moore).

Sorry if my post came off as overly critical. I do appreciate people trying to quantify this stuff, as I said. And I enjoyed reading your findings and write-up. I also certainly didn't mean to imply that you were putting your thumb on the scale. I understand these metrics are objective and that Harvard's returning points per game number is what it is.

However, the fact you chose to base offensive ranking entirely (mostly?) off of returning points per game is not objective. While the inputs themselves may be objective metrics, choosing which inputs to use is necessarily subjective. I don't deny that you are limited in your data and maybe this is the best you can do; but it's very clear if you look past this one statistic that Harvard is once again going to be very talented this season. They still have by far the most draft picks in the ECAC, by the far most players who were in the central scouting rankings, etc. These are imperfect metrics, but they're other metrics that you could consider factoring into your analysis.

By the way, how do you measure incoming class rank? I may have missed that, but I didn't see it in your post. Cornell's incoming class consists of five draft picks, which I believe is easily the most in the ECAC, but its incoming class is ranked #7.

Looking only at the bold statement, my response is ... so what? Judge the model at the end of the year, not now. You're obviously free to have and share an opinion but he's not being more or less subjective than you are. You make good points, BL, about the hidden skill of last year's backups and the incoming class for Harvard but that doesn't make you less subjective than sezenack (yet). It's an interesting discussion, and i like hearing people poke at the assumptions underlying a prediction, but have some sense of when you're sharing your own subjective metrics too.

[BearLover]

An RPI fan and his computer program's ECAC predictions. https://thefieldhouse.substack.com/p/ecac-2023-24-preview?utm_source=profile&utm_medium=reader2

Cornell is #2, and Harvard is #7 below #4 Princeton.

I appreciate that someone is trying to quantify these things rather than making prediction based on feel, but the fact this model ranks Harvard's returning offense as 12th in the league evidences a clear flaw in its methodology, in my opinion. I would guess the issue is that Harvard's top players last year were SO good that they got all the PP time and played a crazy amount of minutes, especially when Harvard needed a goal. So yeah, nearly all the offensive production came from those players, who are gone now. But that doesn't mean the players who played behind them, and will now take on a larger role, are not good players—it just means they didn't add much offensively last year, because they didn't need to.

And though I wish it were true, I just don't see Cornell as an elite team this season. We could compete for an NCAA spot, but if that happens it is most likely as one of the final at-large bids. We have a ton of freshmen, no one who has played more than two years for Cornell (and no one aside from Seger who has played more than two years of college hockey at all). We are still going up against much older and more experienced teams whenever we play a non-Ivy. I like our trajectory but don't expect us to be elite until the fifth-year eligibility rule finally goes away in a couple seasons.

ursusminor told me he posted this here, and I saw this and wanted to reply.

Harvard's 12th ranked returning offense isn't an opinion; it's a fact. They return 122 points and played 34 games, so they return 3.59 points per game, which is last in the league. It's an entirely objective metric. I disagree that it's a flaw in the methodology and think it's much more of a symptom of the lack of college hockey data available to the public (mainly time on ice).

However, I do agree with your points about PP time and general time on ice. Harvard does have good talent that played lower in the lineup that will likely step up. It's entirely possible they beat the projection, and I'd say they are the likeliest team to do that of the 12. Anyone expecting them to maintain their level of last season is mistaken though. Looking at the roster, the only player I see surpassing 30 points is Joe Miller. None of the players that remain are at the level of Coronato, Farrell, or Laferriere. None of the defensemen are at the level of Thrun even though Ian Moore is very good. Those are the players they have to replace, and Harvard isn't equipped to do it regardless of ice time. The players they have are not that caliber, where they put up big numbers and get an NHL deal following the season (with the exception of Miller and Moore).

Sorry if my post came off as overly critical. I do appreciate people trying to quantify this stuff, as I said. And I enjoyed reading your findings and write-up. I also certainly didn't mean to imply that you were putting your thumb on the scale. I understand these metrics are objective and that Harvard's returning points per game number is what it is.

However, the fact you chose to base offensive ranking entirely (mostly?) off of returning points per game is not objective. While the inputs themselves may be objective metrics, choosing which inputs to use is necessarily subjective. I don't deny that you are limited in your data and maybe this is the best you can do; but it's very clear if you look past this one statistic that Harvard is once again going to be very talented this season. They still have by far the most draft picks in the ECAC, by the far most players who were in the central scouting rankings, etc. These are imperfect metrics, but they're other metrics that you could consider factoring into your analysis.

By the way, how do you measure incoming class rank? I may have missed that, but I didn't see it in your post. Cornell's incoming class consists of five draft picks, which I believe is easily the most in the ECAC, but its incoming class is ranked #7.

Looking only at the bold statement, my response is ... so what? Judge the model at the end of the year, not now. You're obviously free to have and share an opinion but he's not being more or less subjective than you are. You make good points, BL, about the hidden skill of last year's backups and the incoming class for Harvard but that doesn't make you less subjective than sezenack (yet). It's an interesting discussion, and i like hearing people poke at the assumptions underlying a prediction, but have some sense of when you're sharing your own subjective metrics too.

No arguments there.

[Swampy]

Is it possible to benchmark the model and possibly improve it, for example by applying it to last year's data and introducing other factors such as each team's average age and class composition?

[David Harding]

Is it possible to benchmark the model and possibly improve it, for example by applying it to last year's data and introducing other factors such as each team's average age and class composition?

I'm sure others have tried ChatGPT.  

User
In what order will the men's ice hockey teams in the EACAHL finish the 2023-2024 season?
ChatGPT

I'm sorry, but I do not have access to real-time or future sports data, including the outcomes of specific sports seasons or events that occurred after my last knowledge update in September 2021. To find out how the men's ice hockey teams in the EACAHL (East Coast Amateur Hockey League) finished the 2023-2024 season, I recommend checking sports news websites, official league websites, or other reliable sources for the most up-to-date information on the league standings and team performance.

User
What are the odds that Cornell will finish the 2023-2024 ECACHL ice hockey season in fiort place.
ChatGPT

I apologize for any inconvenience, but I do not have access to real-time or future sports data, including odds for specific events that occurred after my last knowledge update in September 2021. To find the odds for Cornell finishing in fourth place in the 2023-2024 ECACHL ice hockey season, you should consult sports betting websites, sportsbooks, or other sources that provide up-to-date betting odds and predictions for college ice hockey or specifically for ECACHL. Keep in mind that odds can change frequently based on various factors, so it's important to check with a reliable source for the most current information.

[Al DeFlorio]

Is it possible to benchmark the model and possibly improve it, for example by applying it to last year's data and introducing other factors such as each team's average age and class composition?

I'm sure others have tried ChatGPT.  

User
In what order will the men's ice hockey teams in the EACAHL finish the 2023-2024 season?
ChatGPT

I'm sorry, but I do not have access to real-time or future sports data, including the outcomes of specific sports seasons or events that occurred after my last knowledge update in September 2021. To find out how the men's ice hockey teams in the EACAHL (East Coast Amateur Hockey League) finished the 2023-2024 season, I recommend checking sports news websites, official league websites, or other reliable sources for the most up-to-date information on the league standings and team performance.

User
What are the odds that Cornell will finish the 2023-2024 ECACHL ice hockey season in fiort place.
ChatGPT

I apologize for any inconvenience, but I do not have access to real-time or future sports data, including odds for specific events that occurred after my last knowledge update in September 2021. To find the odds for Cornell finishing in fourth place in the 2023-2024 ECACHL ice hockey season, you should consult sports betting websites, sportsbooks, or other sources that provide up-to-date betting odds and predictions for college ice hockey or specifically for ECACHL. Keep in mind that odds can change frequently based on various factors, so it's important to check with a reliable source for the most current information.

Does fiort place make the playoffs?

[Will]

Is it possible to benchmark the model and possibly improve it, for example by applying it to last year's data and introducing other factors such as each team's average age and class composition?

I'm sure others have tried ChatGPT.  

User
In what order will the men's ice hockey teams in the EACAHL finish the 2023-2024 season?
ChatGPT

I'm sorry, but I do not have access to real-time or future sports data, including the outcomes of specific sports seasons or events that occurred after my last knowledge update in September 2021. To find out how the men's ice hockey teams in the EACAHL (East Coast Amateur Hockey League) finished the 2023-2024 season, I recommend checking sports news websites, official league websites, or other reliable sources for the most up-to-date information on the league standings and team performance.

User
What are the odds that Cornell will finish the 2023-2024 ECACHL ice hockey season in fiort place.
ChatGPT

I apologize for any inconvenience, but I do not have access to real-time or future sports data, including odds for specific events that occurred after my last knowledge update in September 2021. To find the odds for Cornell finishing in fourth place in the 2023-2024 ECACHL ice hockey season, you should consult sports betting websites, sportsbooks, or other sources that provide up-to-date betting odds and predictions for college ice hockey or specifically for ECACHL. Keep in mind that odds can change frequently based on various factors, so it's important to check with a reliable source for the most current information.

Does fiort place make the playoffs?

Maybe it does in the EACAHL.

[billhoward]

I was trying to see if I could build out secondary information on cars, such as specs comparisons, and that was the stumbling block if one wanted to go forward: ChatGPT info looked two years in the rear view mirror. But that's going to change.

[jtwcornell91]

Is it possible to benchmark the model and possibly improve it, for example by applying it to last year's data and introducing other factors such as each team's average age and class composition?

I'm sure others have tried ChatGPT.  

User
In what order will the men's ice hockey teams in the EACAHL finish the 2023-2024 season?
ChatGPT

I'm sorry, but I do not have access to real-time or future sports data, including the outcomes of specific sports seasons or events that occurred after my last knowledge update in September 2021. To find out how the men's ice hockey teams in the EACAHL (East Coast Amateur Hockey League) finished the 2023-2024 season, I recommend checking sports news websites, official league websites, or other reliable sources for the most up-to-date information on the league standings and team performance.

User
What are the odds that Cornell will finish the 2023-2024 ECACHL ice hockey season in fiort place.
ChatGPT

I apologize for any inconvenience, but I do not have access to real-time or future sports data, including odds for specific events that occurred after my last knowledge update in September 2021. To find the odds for Cornell finishing in fourth place in the 2023-2024 ECACHL ice hockey season, you should consult sports betting websites, sportsbooks, or other sources that provide up-to-date betting odds and predictions for college ice hockey or specifically for ECACHL. Keep in mind that odds can change frequently based on various factors, so it's important to check with a reliable source for the most current information.

Does fiort place make the playoffs?

Maybe it does in the EACAHL.

Didn't Darmouth finish in fiort place last year, just ahead of Brom?

[arugula]

Interesting. USCHO has us at 11, Sucks at 15. Sounds about right at least to start and based on last year to some extent. However chn has neither in the top 15.

[Trotsky]

USCHO

CHN

[jtwcornell91]

USCHO

CHN

Which is which?

[Trotsky]

Starting at 11.  Getting there.

[arugula]

Felt like we spent all of last season digging out of the early season hole.

[marty]

Felt like we spent all of last season digging out of the early season hole.

I can dig another season like 2022.