Explore deep learning applications in quantitative finance through this comprehensive ACM conference talk. Gain insights into the quantitative investment process, from raw data input to trade execution, and learn how deep learning sequence methods can be applied to various steps in this pipeline. Discover the fundamentals of feature extraction, return forecasting, portfolio allocation, and trading execution. Delve into sequence modeling, recurrent neural networks, and reinforcement learning in the context of financial decision-making. Examine technical features, qualitative factors, and the challenges of missing data in financial modeling. Discuss the future of reinforcement learning, explainability in deep learning models, and the distinction between deep learning and deep understanding in quantitative finance. No prior knowledge of finance or deep learning is required for this informative session led by David Kriegman, a distinguished computer science professor and industry expert.
Deep Learning for Sequences in Quantitative Finance
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
Introduction
Welcome
Sequences
Quantitative Pipeline
Alpha Modeling
Technical Features
Portfolio Optimization
Execution
Sequence Decision Making
Deep Learning
Deep Network
Sequence Modeling
Quantitative Finance
Recurrent Neural Networks
Reinforcement Learning
QA
Algorithm Adaptation
Qualitative Features
Future of Reinforcement Learning
Deep Learning Models
Distribution in Inference
Missing Data
Deep Learning vs Deep Understanding
Explainability
Taught by
Association for Computing Machinery (ACM)
Related Courses
Related articles
Reviews
5.0 rating, based on 1 Class Central review
-
Deep Learning for Sequences in Quantitative Finance" offers a comprehensive exploration into the intersection of deep learning and financial markets. As an aspiring data scientist in finance, I found the content both rigorous and highly applicable.…
