on analysis and betting

Home for all your discussion of basketball statistical analysis.
Post Reply
vzografos
Posts: 23
Joined: Thu Sep 06, 2018 10:42 am

on analysis and betting

Post by vzografos » Tue Jun 11, 2019 6:05 am

Hi,
not sure if this is a controversial subject, but I was wondering if anyone in here is using statistical analysis and other empirical information to bet on NBA games. As in betting for stable income and not just entertainment.

Crow
Posts: 6134
Joined: Thu Apr 14, 2011 11:10 pm

Re: on analysis and betting

Post by Crow » Wed Jun 12, 2019 6:05 am

Yes, some high frequency or professional gamblers use analytics. Some have occasionally posted here. Usually not revealing much. If you search certain key words you might find some of those posts and names. You could try to contact or generate public discussion but it may or may not work. There are some other sites where such discussions or private discussions may be more possible or common.

If you want pubic discussion, what are you going to reveal to kick it off?

Assuming this is yours...

Discriminative subspace clustering

2013

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

We present a novel method for clustering data drawn from a union of arbitrary dimensional subspaces, called Discriminative Subspace Clustering (DiSC). DiSC solves the subspace clustering problem by using a quadratic classifier trained from unlabeled data (clustering by classification). We generate labels by exploiting the locality of points from the same subspace and a basic affinity criterion. A number of classifiers are then diversely trained from different partitions of the data, and their results are combined together in an ensemble, in order to obtain the final clustering result. We have tested our method with 4 challenging datasets and compared against 8 state-of-the-art methods from literature. Our results show that DiSC is a very strong performer in both accuracy and robustness, and also of low computational complexity.

Does it (or any of your other research) have basketball translations, pursued or not? I am guessing you have skills to get in the game at a certain level or at least style. I dunno what it actually takes to be upper-tier.

vzografos
Posts: 23
Joined: Thu Sep 06, 2018 10:42 am

Re: on analysis and betting

Post by vzografos » Wed Jun 12, 2019 1:03 pm

Crow wrote:
Wed Jun 12, 2019 6:05 am
Yes, some high frequency or professional gamblers use analytics. Some have occasionally posted here. Usually not revealing much. If you search certain key words you might find some of those posts and names. You could try to contact or generate public discussion but it may or may not work. There are some other sites where such discussions or private discussions may be more possible or common.

If you want pubic discussion, what are you going to reveal to kick it off?

Assuming this is yours...
Yes that's me.
My background is computer science and machine learning (what you would call Data science nowadays) so data, stats and predictions are something that interests me.
Also it seems obvious if you want to play around with data and make predictions, it is only natural to take the next step and make some money from it. :mrgreen:

In fact I do not like gambling and I do not understand it. Doesn't do anything for me. I prefer to make predictions, evaluate risk and return and make a trade (or investment or whatever you want to call it).
So my plan is to take as much of the uncertainty and risk from sports betting as possible, and treat it as any other investment or trading product.

So I was hoping that there are some people here from similar backgrounds that might be interested in applying ML in sports data and share their experiences. I will definitely do so myself. Also, if there are people who use their empirical knowledge about the NBA, teams and players I would really like to hear from those as well. See if there is a way to incorporate empirical knowledge to my algorithms.

Post Reply