Sports Analytics Weekly by kubeia.io - 5/2023
- Week 52
- Week 51
- Week 49
- Week 48
- Week 47
- 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 33
- Week 32
- 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 16
- Week 14
- Week 13
- Week 12
- Week 10
- Week 9
- Week 6
- Week 5
- Week 4
- Week 3
- Week 1
🎲 Betting
The army of maths prodigies who helped Brighton conquer the transfer market
yahoo.com
According to one betting industry insider, Bloom was across expected goals modelling “before anyone knew what it was” and will be a good decade further on now into drilling into more detailed questions of a player’s suitability to a team’s wider style.
But here’s the crucial caveat. Bloom is also among the best at understanding the limitations of data, accepting the inherent unpredictability of football and the importance of the human touch both in building a team and keeping staff happy, motivated and loyal.
đź’° Quantitative Finance
Basics Of Options Trading Explained
quantinsti.com
If you think investing in options is just another way to make money and was created by some fancy guys in suits working at Wall Street, you are wrong. The options world predates the modern stock exchanges by a large margin. Some credit the Samurai for giving us the foundation on which options contracts were based. While some others acknowledge the Greeks for providing us with an idea of how to speculate on a commodity; in this case, the harvest of olives. In both cases, humans were trying to guess the price of a food item and trade accordingly (rice in the case of samurais), long before the modern world put in various rules and set up exchanges.
🤖 Machine Learning
Natural Language Processing with Transformers
deepset.ai
Read these free chapters from a popular book published recently by O'Reilly on the real-life applications of the Transformer language models.
From Zero to Research Scientist full resources guide
github.com
This guide is designated to anybody with basic programming knowledge or a computer science background interested in becoming a Research Scientist with 🎯 on Deep Learning and NLP.
Reinforcement Learning for Beginners: Coding a Maze-solving Agent from Scratch
github.io
What could we do if, instead of coding programs from the ground up, we could just specify the rules for a task, the success criteria, and make AI learn to complete it?
Pandas Illustrated: The Definitive Visual Guide to Pandas
betterprogramming.pub
Is it a copy or a view? Should I merge or join? And what the heck is MultiIndex?
7 SMOTE Variations for Oversampling
kdnuggets.com
The imbalanced dataset is a problem in data science. The problem happens because imbalance often leads to modeling performance issues. To mitigate the imbalance problem, we can use the oversampling method. Oversampling is the minority resampling data to balance out the data.
C++ Neural Network in a Weekend
jeremyong.com
Would you like to write a neural network from start to finish? Are you perhaps shaky on some of the fundamental concepts and derivations, such as categorical cross-entropy loss or backpropagation? Alternatively, would you like an introduction to machine learning without relying on “magical” frameworks that seem to perform AI miracles with only a few lines of code (and just as little intuition)? If so, this article was written for you.
đź’» Hardware
Benchmarking Deep Neural Networks for Low-Latency Trading and Rapid Backtesting on NVIDIA GPUs
nvidia.com
Lowering response times to new market events is a driving force in algorithmic trading. Latency-sensitive trading firms keep up with the ever-increasing pace of financial electronic markets by deploying low-level hardware devices like Field Programmable Gate Arrays (FPGAs) and Application Specific Integrated Circuits (ASICs) into their systems. However, as markets become increasingly efficient, traders need to rely on more powerful models like deep neural networks (DNNs) to improve their profitability. Since the implementation of such complex models on low-level hardware devices requires substantial investments, general purpose GPUs present a viable, cost-effective alternative to FPGAs and ASICs.