- Видео 54
- Просмотров 28 672
HKML
Гонконг
Добавлен 14 сен 2020
HKML is an AI-first Group focused on serving its community.
HKML Group sponsors the Hong Kong Machine Learning Meetups.
You can find recording of the events on this RUclips channel in the HKML Meetup playlists.
HKML Group sponsors the Hong Kong Machine Learning Meetups.
You can find recording of the events on this RUclips channel in the HKML Meetup playlists.
Uniform at Heart: Generating Correlation Matrices with the Onion Method
Dive into the core of statistical simulations with our concise and informative RUclips short, where we explain generating random correlation matrices using the Onion Method. This technique stands out for its ability to produce uniformly distributed correlation matrices, a cornerstone for researchers and analysts across various fields including finance, and beyond.
In this video, we:
- Introduce the concept and importance of correlation matrices in statistical analysis and simulations.
- Break down the Onion Method, a step-by-step approach to constructing random, yet uniformly distributed correlation matrices.
- Highlight the unique advantages of this method, ensuring that the matrices generat...
In this video, we:
- Introduce the concept and importance of correlation matrices in statistical analysis and simulations.
- Break down the Onion Method, a step-by-step approach to constructing random, yet uniformly distributed correlation matrices.
- Highlight the unique advantages of this method, ensuring that the matrices generat...
Просмотров: 60
Видео
Master Quant Trading: Unveil the Power of Information Coefficient - HKML EduTech
Просмотров 32810 месяцев назад
🚀 Elevate Your Quant Skills with HKML EduTech 🚀 Welcome to a game-changing journey into the world of quantitative trading. In this exclusive short video, we delve into one of the most critical concepts in quant trading: the Information Coefficient (IC). Understanding IC is key to developing effective and reliable trading strategies. ✨ What You'll Discover in This Video: ✨ The Essence of Informa...
HKML S5E3 - Applied/Production ML/RL for Ads/Recommendations
Просмотров 172Год назад
Applied/Production ML/RL for Ads/Recommendations Abstract: Reinforcement Learning has recently gained popularity with the successes in solving difficult high dimensional problems in games, optimization. However, RL is not limited to game-like problem and covers different range of application as well as a broad science field (from ML theory to Optimal control). So, we highlight key principles of...
HKML S5E3 - Nonlinearities in a multi-factor model framework using Machine Learning by CrunchDAO
Просмотров 317Год назад
Abstract: CrunchDAO's Crowdsourced Investment Framework makes use of supervised learning to predict returns, which are residualized against, i.e., uncorrelated with linear econometric risk models. In order to obtain estimates with the desired properties, in this work we investigate the effect of design choices associated with feature engineering and model training. In particular, the orthogonal...
Fundamental Analysis 2.0: Leveraging Data Science to Enhance Your Investment Process
Просмотров 332Год назад
In this course, you will learn how to use data science techniques to enhance your fundamental analysis process and make more informed investment decisions. You will start by gaining a strong foundation in the basics of data science, including concepts such as data exploration, visualization, and statistical analysis. Next, you will learn how to apply these concepts to real-world equity analysis...
HKML S5E2 - Rajneesh Tiwari, on predicting presence of life-supporting chemical compounds on Mars
Просмотров 115Год назад
Rajneesh leads the Product and Strategy teams at Bulian AI. Before founding Bulian AI, he built multiple machine learning systems at Novartis, Ericsson, and various research-focused startups in India. He had more than a decade worth of experience in building ML systems delivering high impact for customers. Along with pursuing his MS from Georgia Tech, he is also very active on Kaggle and is a p...
HKML S5E2 - Optiver Realized Volatility Prediction competition by Caleb Yung, Kaggle Expert
Просмотров 3,7 тыс.Год назад
Caleb is currently at HSBC as a data scientist focusing on using machine learning to detect financial crime from transactions. In his free time, he enjoys learning AI/ML in competitive environments and is a Kaggle Competition Expert with several competitions ending up in the top 5%. Presentation Introduction: Caleb will present his solution to the Optiver Realized Volatility Prediction competit...
HKML S5E2 - G-Research Kaggle competition by Patrick Yam (Gold medal, ranked 7/1946)
Просмотров 1,5 тыс.Год назад
Patrick Yam worked as a quantitative researcher in a Hedge fund, focusing on solving challenging problems using machine learning. He is a Kaggle competition master (Top 100 on the global competition leaderboard) with 4 gold medals in various Kaggle competitions. Presentation introduction: In the G-Research Crypto Forecasting competition, we used our machine learning expertise to forecast short-...
HKML S5E1 - AI Tech Powering a Hedge Fund by Johan Lundin
Просмотров 2872 года назад
BFAM Partners is a multi-strat hedge fund primarily based in Hong Kong. Behind the hedge fund there is the dedicated AI research company Shell Street Labs. Johan Lundin started working at BFAM Partners in 2018 and transitioned over to Shell Street Labs in 2020 where he leads the engineering team. In this talk he will talk about what tools and technologies that Shell Street Labs is using to powe...
Hierarchical PCA: Incorporate (fundamental) priors into PCA
Просмотров 4422 года назад
PCA is a useful tool for quant trading (stat arb) but in its naive implementation suffers from several forms of instabilities which yield to unnecessary turnover (trading cost...) and spurious trades. In order to regularize the model, several techniques are available. We will discuss one in particular: The Hierarchical PCA (HPCA). With HPCA, we modify the empirical correlation matrix such that ...
HKML S4E8 - Nonstationary Temporal Matrix Factorization for Multivariate Time Series Forecasting
Просмотров 3302 года назад
Nonstationary Temporal Matrix Factorization for Multivariate Time Series Forecasting Speaker: Xinyu Chen Abstract: Modern time series datasets are often high-dimensional, incomplete/sparse, and nonstationary. These properties hinder the development of scalable and efficient solutions for time series forecasting and analysis. To address these challenges, we propose a Nonstationary Temporal Matri...
HKML S4E7 - Pricing options on flow forwards by neural networks in Hilbert space
Просмотров 4372 года назад
Pricing options on flow forwards by neural networks in Hilbert space Speaker: Luca Galimberti Abstract: We propose a new methodology for pricing options on flow forwards by applying infinite-dimensional neural networks. We recast the pricing problem as an optimization problem in a Hilbert space of real-valued function on the positive real line, which is the state space for the term structure dy...
HKML EduTech - Introduction Crypto Telegram Bot by Chris Kang
Просмотров 4152 года назад
HKML EduTech - Introduction Crypto Telegram Bot by Chris Kang
HKML S4E6 - From galaxy pairs to galaxy mergers
Просмотров 772 года назад
HKML S4E6 - From galaxy pairs to galaxy mergers
HKML S4E6 - Sequential Bootstrapping in Finance: Approaching the true IID Sampling
Просмотров 3772 года назад
HKML S4E6 - Sequential Bootstrapping in Finance: Approaching the true IID Sampling
HKML S4E5 - Information geometry & adaptive assessment
Просмотров 1252 года назад
HKML S4E5 - Information geometry & adaptive assessment
HKML EduTech - Algorithm & Data Structure - Training for Coding Interviews
Просмотров 3672 года назад
HKML EduTech - Algorithm & Data Structure - Training for Coding Interviews
HKML S4E4 - 3D Infomax improves GNNs for Molecular Property Prediction by Hannes Stark
Просмотров 1562 года назад
HKML S4E4 - 3D Infomax improves GNNs for Molecular Property Prediction by Hannes Stark
HKML S4E4 - Asset Pricing with Panel Trees under Global Split Criteria by Sean Xin He
Просмотров 1992 года назад
HKML S4E4 - Asset Pricing with Panel Trees under Global Split Criteria by Sean Xin He
HKML S4E4 - Top2Vec: Distributed Representations of Topics, with application on 2020 10-K
Просмотров 7432 года назад
HKML S4E4 - Top2Vec: Distributed Representations of Topics, with application on 2020 10-K
HKML S4E3 - AI Automation and how it's a game-changer on the way we apply AI to Business (DataRobot)
Просмотров 792 года назад
HKML S4E3 - AI Automation and how it's a game-changer on the way we apply AI to Business (DataRobot)
HKML S4E3 - Application of Natural Language Processing to financial text to create alternative data
Просмотров 2572 года назад
HKML S4E3 - Application of Natural Language Processing to financial text to create alternative data
HKML S4E2 - A machine learning approach for predicting hidden links in supply chain with GNNs
Просмотров 4033 года назад
HKML S4E2 - A machine learning approach for predicting hidden links in supply chain with GNNs
HKML S4E2 - AutoGL - An autoML framework & toolkit for machine learning on graph
Просмотров 2953 года назад
HKML S4E2 - AutoGL - An autoML framework & toolkit for machine learning on graph
HKML S4E1 - FastSHAP: Real-Time Shapley Value Estimation by Ian Covert
Просмотров 9313 года назад
HKML S4E1 - FastSHAP: Real-Time Shapley Value Estimation by Ian Covert
HKML S4E1 - Introduction to Darwinex by its CEO Juan Colón
Просмотров 1823 года назад
HKML S4E1 - Introduction to Darwinex by its CEO Juan Colón
HKML S4E1 - Using 10-K and NLP for investment strategies by Lucas Krenn
Просмотров 5723 года назад
HKML S4E1 - Using 10-K and NLP for investment strategies by Lucas Krenn
HKML S3E12 - PAGnol: A French extreme-scale model by Julien Launay
Просмотров 2013 года назад
HKML S3E12 - PAGnol: A French extreme-scale model by Julien Launay
HKML S3E12 - Bayesian Modeling without the Math by Alexandre Andorra
Просмотров 3403 года назад
HKML S3E12 - Bayesian Modeling without the Math by Alexandre Andorra
3% IC is trashhhhh you should be getting 10% or higher and 20% if using nonlinear methods lmao
It's paid or free
Thank you for explaining this concept. I want to know why do we want to confuse the discriminator network after receiving prior distribution or bottleneck learned data?
Good for machine learning recommendation
27:00 tsfresh
Thank you for sharing.
ρяσмσѕм
Very interesting Patrick, good job !
Thank you for sharing.
Thanks for posting these kind of content! However, I think there is a problem with the audio and this video and it'd be real nice if you can solve this issue (if you ment to upload it with audio of course!). Thx!
Very nice
ƤＲＯ𝓂Ｏ𝕤ᗰ 🎊
You have not mentioned that how to deal with long financial report?
Thanks for pointing that out. It is quite a challenge indeed! Please, direct your question to the speaker directly as he may be in position to answer? We are aware of some unpublished techniques, but those are proprietary details we cannot share.
@@hkml-group Ok I'll try to contact them and thankyou for responding.
Great overview of the field!
Thank you Edward for the talk.
You are producing very nice videos ... keep it up guys... love from India ❤️
Thank you for sharing.
Do you have an example of how to get the probability outputs? This would be incredibly helpful, thanks for the video!
Great job organizing such useful talks.
Our pleasure
Very informative, thank you for sharing.
Glad you enjoyed it!
Thank you for having us on!
The problem I see with using GAN data in finance is that the generator is bound to generate artifacts that makes the data unusable ,