Sports Analytics Weekly by kubeia.io - 37/2023

Evan Hansen was born to play football. A strong, rambunctious kid, he started playing sports year-round as early as he could. “He was very selfless, always willing to sacrifice himself for the betterment of the team,” says his father, Chuck Hansen. As a fearless linebacker at Wabash College in Indiana, the young player made 209 tackles in his first three seasons, and was hit far more than that during games and practices. Two days after winning the second game of his senior year, Evan died by suicide.

An honest, no-stone-unturned interview with Charlotte Randall, COO and Co-Founder of StatsBomb.

The lasting legacy of Moneyball is as an exemplar of the possibilities of competitive advantage to be gained from the smarter use of data analytics as part of an evidence-based approach to decision-makingThe technical essence of Moneyball is using on-base percentage (OBP) as the primary hitter metric in baseball for player recruitmentMoneyball shows how Billy Beane and the Oakland A’s developed a David strategy to take advantage of the inefficiency of other MLB teams in valuing the win contributions of players.

Financial determinism in pro team sports is the basic proposition that the financial power to acquire top playing talent determines sporting performance (sport’s “ law of gravity”)The Oakland A’s under Billy Beane have consistently defied the law of gravity for over a quarter of a century by using a “David strategy” of continuous innovation based on data analytics and creativity

Several recent studies suggest that the home advantage, that is, the benefit competitors accrue from performing in familiar surroundings, was—at least temporarily—reduced in games played without spectators due to the COVID-19 Pandemic. These games played without fans during the Pandemic have been dubbed ‘ghost games’. However, the majority of the research to date focus on soccer and no contributions have been provided for indoor sports, where the effect of the support of the fans might have a stronger impact than in outdoor arenas. In this paper, we try to fill this gap by investigating the effect of ghost games in basketball with a special focus on the possible reduction of the home advantage due to the absence of spectators inside the arena. In particular, we test (i) for the reduction of the home advantage in basketball, (ii) whether such reduction tends to disappear over time, (iii) if the bookmakers promptly adapt to such structural change or whether mispricing was created on the betting market. The results from a large data set covering all seasons since 2004 for the ten most popular and followed basketball leagues in Europe show, on the one hand, an overall significant reduction of the home advantage of around 5% and no evidence that suggests that this effect has been reduced at as teams became more accustomed to playing without fans; on the other hand, bookmakers appear to have anticipated such effect and priced home win in basketball matches accordingly, thus avoiding creating mispricing on betting markets.

Travis Hunter, much like baseball’s Shohei Ohtani, burst onto the scene for Colorado by taking snaps on offense and defense - averaging over 60 plays per game on each side of the ball over the Buff’s first two games - upending the traditional understanding of a player’s position. Hunter is the most extreme example of the growing trend of positional flexibility in football, exemplified by Kyle Shanahan’s use of Deebo Samuel, Kyle Juszczyk, and Christian McCaffrey for the 49ers, Cordarrelle Patterson for the Falcons, and even Frank Gore Jr. at Southern Miss.How StatsBomb handles multi-position players

Today, our AI team are going to talk you through one of the cornerstones our of tracking data collection methodology – homography estimation.

Accurately localizing objects in three dimensions (3D) is crucial for various computer vision applications, such as robotics, autonomous driving, and augmented reality. This task finds another important application in sports analytics and, in this work, we present a novel method for 3D basketball localization from a single calibrated image. Our approach predicts the object's height in pixels in image space by estimating its projection onto the ground plane within the image, leveraging the image itself and the object's location as inputs. The 3D coordinates of the ball are then reconstructed by exploiting the known projection matrix. Extensive experiments on the public DeepSport dataset, which provides ground truth annotations for 3D ball location alongside camera calibration information for each image, demonstrate the effectiveness of our method, offering substantial accuracy improvements compared to recent work. Our work opens up new possibilities for enhanced ball tracking and understanding, advancing computer vision in diverse domains. The source code of this work is made publicly available at \url{this https URL}.

Goldman Sachs Exchanges: Great Investors A conversation with Renaissance Technologies CEO Peter Brown. Raj Mahajan, global head, Systematic Client Franchise, Global Banking & Markets, Goldman Sachs. Date of recording: July 27, 2023.

Large Language Models (LLMs), prominently highlighted by the recent evolution in the Generative Pre-trained Transformers (GPT) series, have displayed significant prowess across various domains, such as aiding in healthcare diagnostics and curating analytical business reports. The efficacy of GPTs lies in their ability to decode human instructions, achieved through comprehensively processing historical inputs as an entirety within their memory system. Yet, the memory processing of GPTs does not precisely emulate the hierarchical nature of human memory. This can result in LLMs struggling to prioritize immediate and critical tasks efficiently. To bridge this gap, we introduce an innovative LLM multi-agent framework endowed with layered memories. We assert that this framework is well-suited for stock and fund trading, where the extraction of highly relevant insights from hierarchical financial data is imperative to inform trading decisions. Within this framework, one agent organizes memory into three distinct layers, each governed by a custom decay mechanism, aligning more closely with human cognitive processes. Agents can also engage in inter-agent debate. In financial trading contexts, LLMs serve as the decision core for trading agents, leveraging their layered memory system to integrate multi-source historical actions and market insights. This equips them to navigate financial changes, formulate strategies, and debate with peer agents about investment decisions. Another standout feature of our approach is to equip agents with individualized trading traits, enhancing memory diversity and decision robustness. These sophisticated designs boost the system's responsiveness to historical trades and real-time market signals, ensuring superior automated trading accuracy.

Seasonality effects, one of the most fascinating phenomena in the world of finance, have captured the attention of investors and researchers worldwide. Since these anomalies are often driven by factors other than general market trends, they usually don’t correlate strongly with market movements, which can help reduce the portfolio’s overall risk. Following the theme of our previous article Are There Seasonal Intraday or Overnight Anomalies in Bitcoin?, we decided to extend the data and conduct a more in-depth analysis of our earlier findings. This article explores potential seasonal patterns related to Bitcoin, focusing on whether these patterns are influenced by factors such as current market trends or the level of volatility in the market.

Class imbalance is not a problem, the use of incorrect metrics, uncalibrated classifiers and methods like smote are problems.

Puncc (Predictive uncertainty calibration and conformalization) is an open-source Python library that integrates a collection of state-of-the-art conformal prediction algorithms and related techniques for regression and classification problems. It can be used with any predictive model to provide rigorous uncertainty estimations. Under data exchangeability (or i.i.d), the generated prediction sets are guaranteed to cover the true outputs within a user-defined error alpha.

In the AI landscape of 2023, vector search is one of the hottest topics due to its applications in large language models (LLM) and generative AI. Semantic vector search enables a broad range of important tasks like detecting fraudulent transactions, recommending products to users, using contextual information to augment full-text searches, and finding actors that pose potential security risks.Data volumes continue to soar and traditional methods for comparing items one by one have become computationally infeasible. Vector search methods use approximate lookups, which are more scalable and can handle massive amounts of data more efficiently. As we show in this post, accelerating vector search on the GPU provides not only faster search times, but the index building times can also be substantially faster.

The title of this book is “Understanding Deep Learning” to distinguish it from volumes that cover coding and other practical aspects. This text is primarily about the ideas that underlie deep learning. The first part of the book introduces deep learning models and discusses how to train them, measure their performance, and improve this performance. The next part considers architectures that are specialized to images, text, and graph data. These chapters require only introductory linear algebra, calculus, and probability and should be accessible to any second-year undergraduate in a quantitative discipline. Subsequent parts of the book tackle generative models and reinforcement learning. These chapters require more knowledge of probability and calculus and target more advanced students.

When programming day to day in C++ , we frequently take for granted the hardware instructions we're creating. You may have heard that system calls are expensive, but do you know what a system call actually does? You may have heard of calling conventions, but do you know what that looks like in practice? All too often we take these and other aspects of our systems as a kind of uninvestigated lore. In this talk we're taking a deep dive into how computers work when you strip off the veneer of C++ code. We'll cover assembly basics and delve into system calls, calling conventions, atomics, and other low-level aspects of computer hardware. Our primary focus will be x86-64/Linux, but we'll touch on Arm and other operating systems where relevant.

It is not often that a sports book becomes a national bestseller in the business book lists but Michael Lewis has achieved that unusual feat with Moneyball: The Art of Winning an Unfair Game (Norton, London, 2003). Moneyball has caused as much interest and controversy in American B-Schools as it has at the ballpark. Why? It tells the David-and-Goliath story of how a small-market team, the Oakland A’s, is taking on the New York Yankees and the other big-market baseball teams and winning, regularly getting to the post-season playoffs on a player budget only around a quarter of that of the Yankees. It’s about trying to do things differently to create a sustainable competitive advantage. Moneyball is a case study of successful corporate strategy, organisational learning and industry resistance to change, and set in the context of America’s traditional pastime. Little wonder that it has had such an appeal to B-Schools.

Moneyball was a game-changer in raising general awareness of the possibilities for data analytics in elite sport.Always remember that Moneyball is only “based on a true story” and does not provide an authentic representation of how data analytics developed at the Oakland A’s.The conflict between scouting and analytics is exaggerated for dramatic effect.The real lesson of Moneyball is the value of an evidence-based approach. This goes beyond the immediate context of player recruitment in pro baseball to embrace all coaching decisions in all sports.

Let's delve into the brilliant world of Bayes' theorem, a cornerstone of probability and modern machine learning. Hold tight, we're making it simple!

Even more than statistics, causal Inference is the true mathematical language of science

The law of large numbers is frequently misunderstood.We use it quite often, but there is an important caveat. Although the sample average (almost surely) converges to the expected value, the speed of the convergence depends on the variance of our sample. The larger the variance, the slower the convergence.This is bad news for many practical applications. For instance, this is why the convergence of the Monte Carlo method is slow. In a real-life scenario, like gambling, you might even run out of money before you finally start winning. (Though most casino games have a negative expected value, so you’ll always lose on the long run.)

The Lindy effect is a statistical tendency for things with longer pasts behind them to have longer futures ahead. It has been experimentally confirmed to apply to some categories, but not others, raising questions about when it is applicable and why. I shed some light on these questions by examining the mathematical properties required for the effect and generating mechanisms that can produce them. While the Lindy effect is often thought to require a declining hazard rate, I show that it arises very naturally even in cases with constant (or increasing) hazard rates -- so long as there is a probability distribution over the size of that rate. One implication is that even things which are becoming less robust over time can display the Lindy effect.