-
Notifications
You must be signed in to change notification settings - Fork 10
2. Devise and Pit.AI Technologies
Table of Contents
Our mission at Pit.AI Technologies is to solve intelligence for investment management. In other words, we are building machine learning algorithms to automate all steps in the investment management process, from generating trading ideas to capital allocation.
We break this down into three independent but equally important problems: building the eyes of our AI, building the brain of our AI, and building an AI fund manager.
The goal here is to aggregate as much price sensitive data as possible into low dimensional features that are as useful for finding investment opportunities as the original raw data. This is so that we may empower our AI with as much price sensitive information as a human Quant would have access to, but without overwhelming our AI computationally. Said differently, we are bridging the information gap between humans (Quants) and our AI, under a feature budget constraint.
The best analogy is how we make sense of images. Images are made of pixels, yet when the human brain attempts to make sense of charts on a Bloomberg terminal, or news articles online, it does not make sense of pixels individually, which would be computationally impractical. Instead, the human brain makes sense of features/representations such as curves, levels, shapes, faces, sentiment in a text, etc.
The objective here is to continuously learn from the features coming out of the eyes of our AI, trading strategies that perform as closely as possible to a set of user-specified performance criteria such as Sharpe ratio, annualized return, maximum drawdown etc.
The outputs of this stage are trading strategies whose number keeps growing over time.
The goal of the AI fund manager is to dynamically optimize capital allocation across strategies found by our AI traders.
Essentially, every hedge fund solves two problems as part of the investment process: i) how to find multiple tradable market inefficiencies or trading ideas/strategies and ii) how to optimize capital allocation to found inefficiencies. Solving intelligence for investment management requires having good working solutions for both problems.
Every trading strategy can be regarded as a synthetic asset that can be bought (by following strategy decisions) and sold (by betting against strategy decisions). Finding market inefficiencies is therefore equivalent to engineering blue-chip assets, and allocating capital to found inefficiencies is equivalent to investing in engineered assets (actively or passively).
Devise monetizes our AI's ability to engineer blue-chip assets, while the AI-powered hedge fund monetizes our AI's ability to generate an active-premium over passive strategies on our engineered blue-chip assets. Crucially, the former doesn't present an opportunity cost for the latter as the number of access to Devise is capped so as to prevent found inefficiencies from becoming priced-in.