talk-data.com
People (7 results)
See all 7 →Activities & events
| Title & Speakers | Event |
|---|---|
|
Exercise: using Hidden Markov Model (HMM) for regime detection/prediction.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on exercise applying Hidden Markov Models for regime detection in time series. |
|
|
Generative AI vs Discriminative AI: theory and examples. Semi-supervised learning.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Comparison of generative vs discriminative AI and semi-supervised learning concepts. |
|
|
Exercise: build, finetune, and apply the Lag-Llama transformer.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on exercise to build, fine-tune, and apply the Lag-Llama transformer to time-series data. |
|
|
Deep Autoregressive Models and Transformers
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Discussion on deep autoregressive models and transformer architectures for time-series applications. |
|
|
Exercise: building a poor person's transformer and applying it to time series prediction.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on exercise building a lightweight transformer for time-series prediction. |
|
|
Discriminative AI (supervised learning): CART and neural nets.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Overview of discriminative AI methods including CART decision trees and neural networks for trading data. |
|
|
Exercise: using TimeVAE to predict SPX returns.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on exercise applying TimeVAE to predict SPX returns. |
|
|
Deep Latent Variable Models: Variational Autoencoder (VAE) for time series
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Overview of VAEs and their application to time-series data. |
|
|
Exercise: features engineering using TA-LIB. Building a gradient-boosted tree (GBT) to predict SPX returns.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on feature engineering with TA-LIB and building a gradient-boosted tree to predict SPX returns. |
|
|
LLM for creating and backtesting trading strategies
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Using GenAI/LLMs to create and backtest trading strategies. |
|
|
Exercise: building RNN to predict SPX returns. Performance metrics and comparison.
2025-11-23 · 04:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on exercise building an RNN to predict SPX returns and evaluating performance metrics. |
|
|
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
Hands-on exercise applying Gaussian Mixture Models for regime detection in time series. |
|
|
Beyond LLM: GenAI for Trading and Asset Management
2025-11-21 · 18:00
Ernest (Ernie) P. Chan
– Founder
@ Predictnow.ai; QTS Capital Management
In the news, GenAI is usually associated with large language models (LLMs) or with image generation tools, essentially, machines that can learn from text or images and generate text or images. But in reality, these models can learn from many different types of data. In particular, they can learn from time series of asset returns, which is perhaps the most relevant for asset managers. In this talk, and in our accompanying book (Generative AI for Trading and Asset Management), we highlight both the practical applications and the fundamental principles of GenAI, with a special focus on how these technologies apply to trading and asset management. |
London Seminar: Beyond LLM: GenAI for Trading and Asset Management
|