Sloan 2026 research papers

[Crow]

Research paper abstract:

"Deep Reinforcement Learning for NBA Player Valuation: A Temporal Difference Approach with Shapley Attribution

This paper introduces a deep reinforcement learning framework for evaluating NBA players that learns context-dependent player value directly from game outcomes. Using temporal-difference learning with a distributional win-probability model, the approach estimates how actions and player presence influence expected outcomes across game states. We combine this with a neural Shapley value attribution method to fairly decompose team success into individual contributions while capturing interaction and synergy effects. Empirical results show improved predictive accuracy, greater stability than RAPM, and systematic identification of defensive value and player synergies that traditional metrics fail to capture."


Posters


"Scouting Anyone: Probabilistic Player Archetypes for Any League

This paper introduces a probabilistic framework for identifying basketball player archetypes that can be applied across leagues, including those without access to advanced data. While player segmentation is not new in basketball analytics, we propose a fundamentally different approach based on Archetypal Analysis, which identifies extreme and interpretable player profiles and models players as probabilistic mixtures of these archetypes, explicitly capturing hybrid roles and stylistic flexibility. "


"HoopEval: Individual Player Action Evaluation via Deep Reinforcement Learning

This paper presents HoopEval, a deep reinforcement learning framework for evaluating individual player actions in basketball using spatio-temporal tracking data. The approach models game dynamics and player interactions to estimate the value of both on-ball and off-ball decisions within their tactical context. By decomposing possession-level outcomes into fine-grained action evaluations, HoopEval provides interpretable measures of decision quality beyond traditional statistics. The results demonstrate its potential to support tactical analysis, player development, and data-driven coaching."

Don't think the papers are available yet, at least on Sloan site.

[Mike G]

Do these presentations have authors?

[Crow]

Lots of them.

https://www.sloansportsconference.com/r ... ompetition

https://www.sloansportsconference.com/r ... ompetition

[Crow]

First paper mentioned had a download link I used but can't re-find. None of the others have links to my knowledge.

Saw very little news coverage. None about analytics that really caught my attention.
Break-out sessions will probably appear in youtube in a week or month. Watched a bit of the main stage stuff. Steven Adams said analytics can give players options.

[Crow]

Sounds good broadly but no results shared:

https://cdn.prod.website-files.com/68d6 ... arning.pdf


Reasonable approach for scouting on European data:

https://cdn.prod.website-files.com/68d6 ... League.pdf

[Crow]

Deep Reinforcement Learning for NBA Player Valuation: A Temporal Difference Approach with Shapley Attribution


brief clips and from article:

'Better player evaluation than by regression, more defensive value recognized, player synergies...'

"Can a reinforcement learning system infer player value
directly from game outcomes without predefined action weights?"

"clutch-time actions
showing 40 percent higher variance in impact than identical plays earlier in games"

"Synergy analysis further reveals 127 statistically significant player
interactions (p < 0.05) not captured by additive models"

"Can Shapley value attribution effectively decompose team outcomes into individual
contributions while preserving interaction effects?"

"The most striking finding is the substantial undervaluation of offensive rebounds and steals in
traditional metrics" With offensive rebounds surpassing steals.utilization?

Value decomposition by actions

https://cdn.prod.website-files.com/68d6 ... r.docx.pdf

Really looking for learned review / feedback on this paper.

[Crow]

Most or all Sloan panels and papers are up


https://www.youtube.com/@42analytics/videos


Here is the Deep Reinforcenent Learning presentation:

https://youtu.be/JjeFktc4QLM?si=7X1gNfY9D3_HLE8i