Sports Analytics Weekly by kubeia.io - 38/2024
- Week 46
- Week 45
- Week 44
- Week 43
- Week 42
- Week 41
- Week 40
- Week 39
- Week 38
- Week 37
- Week 36
- Week 35
- Week 34
- Week 31
- Week 30
- Week 29
- Week 28
- Week 27
- Week 26
- Week 25
- Week 24
- Week 23
- Week 22
- Week 21
- Week 20
- Week 19
- Week 18
- Week 17
- Week 16
- Week 15
- Week 14
- Week 13
- Week 12
- Week 11
- Week 10
- Week 9
- Week 8
- Week 7
- Week 6
- Week 5
- Week 4
- Week 3
- Week 2
- Week 1
📝 Sports Analytics
Defensive philosophies in CFB
statsbomb.com - Shane Regel
Last week I used StatsBomb data to look at variations in formation, personnel, and motion usage on offense. This week I am turning my attention to the defense. Similar to what we do for offensive formation, the StatsBomb data science team has built models that use player location tracking data to classify fronts, blitz, and coverage type. In this article I will use the data from these models to examine defensive philosophies from 2023, focusing on blitz and coverage type, to try and find teams to keep an eye on for this season as we move past a lot of the week one and two FCS games and into the conference schedules.
The Mets are looking to hire a data scientist
columbia.edu - Andrew Gelman
The New York Mets are seeking a Senior Data Scientist in Baseball Analytics. The Senior Data Scientist will build, test, and present statistical models that inform decision-making in all facets of Baseball Operations. This position requires strong background in complex statistics and data analytics, as well as the ability to communicate statistical model details and findings to both a technical and non-technical audience. Prior experience in or knowledge of baseball is a plus, but is not required.
👁️ Computer Vision
Build an AI/ML Football Analysis system with YOLO, OpenCV, and Python
youtube.com
In this video, you'll learn how to use machine learning, computer vision and deep learning to create a football analysis system. This project utilizes YOlO a state of the art object detector to detect the players, referees and footballs. It also utilizes trackers to track those object across frames. We also train our own object detector to enhance the output of the state-of-the-art models. Additionally, we will assign players to teams based on the colors of their t-shirts using Kmeans for pixel segmentation and clustering. We will also use optical flow to measure camera movement between frames, enabling us to accurately measure a player's movement. Furthermore, we will implement perspective transformation to represent the scene's depth and perspective, allowing us to measure a player's movement in meters rather than pixels. Finally, we will calculate a player's speed and the distance covered. This project covers various concepts and addresses real-world problems, making it suitable for both beginners and experienced machine learning engineers.In this video you will learn how to:1. Use ultralytics and YOLOv8 to detect objects in images and videos.2. Fine tune and train your own YOLO on your own custom dataset.3. Use KMeans to cluster pixles and segment players from the background to get the t-shirt color accurately. 4. Use optical flow to measure the camera movement. 5. Use CV2's (opencv) perspective transformation to represent the scene's depth and perspective. 6. Measure player's speed and distance covered in the image.
🤖 Machine Learning
TabKANet: Tabular Data Modelling with Kolmogorov-Arnold Network and Transformer
arxiv.org - Weihao Gao, Zheng Gong, Zhuo Deng, Fuju Rong, Chucheng Chen, Lan Ma
Abstract:Tabular data is the most common type of data in real-life scenarios. In this study, we propose a method based on the TabKANet architecture, which utilizes the Kolmogorov-Arnold network to encode numerical features and merge them with categorical features, enabling unified modeling of tabular data on the Transformer architecture. This model demonstrates outstanding performance in six widely used binary classification tasks, suggesting that TabKANet has the potential to become a standard approach for tabular modeling, surpassing traditional neural networks. Furthermore, this research reveals the significant advantages of the Kolmogorov-Arnold network in encoding numerical features. The code of our work is available at this https URL.