qplum
Our dream is to make investing a science ... not a competition, but a truly inclusive process. The way we can come together to achieve this is to make investment management more (1) Thorough (2) Efficient (3) Transparent. Means: A.I and Tech
The next ten years:
Deep Learning in Trading
Disclosures: qplum LLC is a registered investment adviser. Information presented is for educational purposes only and does not intend to make an offer or solicitation for the sale or purchase of any specific securities, investments, or investment strategies. Investments involve risk and, unless otherwise stated, are not guaranteed. Be sure to first consult with a qualified financial adviser and/or tax professional before implementing any strategy discussed herein. Past performance is not indicative of future performance.
Building a machine that trades and adapts to new data.
What we will cover today
What we will not cover today
Specific trading strategies
Humans vs AI
Recommendations about specific stocks
Bitcoin!
I owe everything to
My mentors: Dr. Sudipto Guha, Dr. Michael Steele, Dr. Manindra Agrawal, Dr. Michael Kearns ...
My colleagues: Prashant Lal, Ankit Awasthi, William Chuang,
Taranbir Singh, Saurav Jindal ...
My friends: Mansi Singhal, Rakesh Kumar, Nikhil Jain, Madhur Ambastha ...
Outline
Aim: doing something new in asset management
It can be done ... proof: HFT
How to do it today ... Deep Learning
Some background
Assets managed globally: $164 trillion +
Fees charged : more than $1 trillion a year
Most of it is gut feeling and chasing "experts"
High Frequency Trading
Why, How, What
High Frequency Trading was the first end-to-end application of computer science to trading.
What is High Frequency Trading
How did we apply CS to Trading?
- Better models for short-term prediction ( Data Science not quant )
- Flawless engineering
- Faster Inference
Data Science not Quant
Flawless Engineering
- Millions of lines of optimized C++ coding
- Test-driven development
- Build a simulation environment first
- container technology for deployment
- walk-forward strategies ... (automated model retraining in backtest)
- Big Data technologies
- Software Engineering - good design
Faster Inference
- FPGA programming
- Network Interfaces
- Kernel bypass
- Inter Process Communication
- Shared memory
- Lockfree messaging
- Low latency C++ programming
- Writing code on the NIC
- Better caching
- Round trip time under 3.5 microseconds
Fast for HFT ~ Tall for Basketball
Credits: Pinterest, Blogspot
Why did it work?
Efficiency
Disrupting two huge business lines:
- Inter-dealer brokerage industry
- Traders at banks
Why did it work?
Questions so far?
Job Trends
Nobody wants traders
Nationwide job postings of traders
(Almost) nobody wants quants
Nationwide job postings of quantitative analysts
Machine Learning is booming
Nationwide postings of Machine Learning jobs
Artificial Intelligence is sky-rocketing
Nationwide postings of AI jobs
FinTech!
Nationwide postings of FinTech jobs
Deep Learning in Trading
How would we use Deep Learning in trading?
Why Deep Learning specifically?
Why is it so far behind in asset management?
Why is it picking up now?
Investing with a trustworthy tool
The tool should look at every aspect of the data.
The tool should be affordable and efficient.
The tool should know what we have learned already.
- Benjamin Graham , Towards the science of security analysis, 1952
... and it should keep learning
The answer is ... Deep Learning
Questions?
gchak@qplum.co
Disclosures: qplum LLC is a registered investment adviser. Information presented is for educational purposes only and does not intend to make an offer or solicitation for the sale or purchase of any specific securities, investments, or investment strategies. Investments involve risk and, unless otherwise stated, are not guaranteed. Be sure to first consult with a qualified financial adviser and/or tax professional before implementing any strategy discussed herein. Past performance is not indicative of future performance.
The next ten years: Deep Learning in Trading
By qplum
The next ten years: Deep Learning in Trading
In this talk at Univ. of Pennsylvania, Gaurav will talk about some job trends in financial services to start and cover the transformational impact of A.I. and Deep Learning in making trading a scientific process. Deep learning has been very successful in social sciences and specially areas where there is a lot of data. Trading and investment management fits this paradigm perfectly. It is a social science and not a pure science, and we are generating petabytes of data everyday making it tough to learn from. With the advent of Deep Learning and Big Data technologies for efficient computation, we are finally able to use the same methods in investment management as we would in face recognition or making chatbots. This focus on learning a hierarchical set of concepts is truly making investing a scientific process, a utility.
