TRADING STRATEGIES

We are experienced institutional, electronic traders and have developed automated, electronic trading models in equities and credit generating and sending thousands (to tens of thousands) of two-sided markets in real time to the relevant ECNs/ATSs and auto-hedging positions as well as updating current positions. The model was first developed in 2013 when analysis was complete, back tested the concepts, and generated a theoretical return of ~25%. Since then, it has been deployed executing live trades in an ETF arbitrage trading strategy in credit (LQD vs its components) that generated 30% live returns over the benchmark (S&P 500 corporate bond index) in a delta neutral strategy over a 1-year period.

The model deploys a proprietary, AI-based approach that encapsulates trader logic in technical objects executing across the universe of liquidity and is only bound by access to data and technical resources (grid). Logical processes include the following components (captured in technical objects); rating, structure, curve, liquidity, risk, exposure, flow, momentum and relative strength, fundamentals, position, capital limits, maximum loss, profit target, hedging, hedge composition and value, bid/ask spread capture, securities lending, corporate actions, and holding period. The model can be deployed in ETF create/redeem, ETF arbitrage, market making, flow trading, and relative value strategies.

INVESTOR DECK

While the current version of the model uses AI, next versions of the model will deploy significant improvements including the use of machine learning and deployment across a next-generation technical stack including an in-memory database (like MongoDB, KDB, ParExel, or McObject) and software defined memory through Kove. We have applied these same concepts and technologies to a real-time risk solution deploying a monte carlo simulation that executed over 837 million transactions per second on a 4 server COTS grid (see Kove-McObject-Fultech Real-Time Risk Solution). While the current model focuses in the credit space, these same concepts can be applied to other asset classes (see IWM Equities Strategy) as well and combined with a machine learning approach applied to the model input components to optimize them based on market conditions will produce market transformational opportunities.

Live Electronic Trading Model Screenshot

Delta Neutral IWM Equities Strategy

Coming soon!

Demonstration of Order Entry Console Paul Constantino

This video briefly shows the engine behind our ETF Arbitrage Strategies, with both stocks and IG Bonds. We are currently generating over 250% per annum on these strategies with smooth equity curves. Contact me for more information. investor@quantiverse-ai.net

AI-based, ETF Arbitrage Trading Strategy in high grade corporate bonds, presented by Quantiverse-ai

This video highlights our ground breaking disruptive strategy ETF Arbitrage Trading Strategy currently being deployed in the ETF LQD, a 9 Trillion USD high grade corporate bond market, and the IWM ETF, which is the well known Russell 2000 equities index. Our equity curve and ROI are phenominal, with drawdowns less than 3% with no losing months. For more information, please contact frederick.weiss@quantiverse-ai.com for more information and a live demo with our Portfolio Manager.

Our view on risk

IG Bond trading Strategy demonstration – in process

Get In Touch

Feel better with an approach that resonates with you