Our Story

Trading has evolved from subjective, trader discretion based approach to new objective, systematic strategies that  rely purely on data and algorithms. With this evolution, the demand for quantitative researchers to discover and implement newer trading ideas is also on the rise, but access to these opportunities is available only to a few.

Auquan is started with the aim of making algorithmic trading skills accessible to everyone. We believe that extremely talented people equipped with right knowledge can design highly successful  quantitative strategies. And we’re doing just that, democratizing algorithmic trading technology to enable any engineer to design a strategy.

We are a small, bootstrapped team; if you believe in our vision we'd love your help, please contact us.

What is our approach?

We restructure trading into a data and math problem by abstracting finance domain knowledge out of the problem. This allows data scientists to analyze years of historical data to discover patterns and build predictive models without any experience in finance.
Auquan facilitates development by providing its users with free tools and datasets that they will need to uncover patterns in the data. Any finance knowledge in built into the dataset, and our users can simply draw on skills from their fields to solve the data-driven problem. Auquan uses these user-created models to create a superior ensemble strategy, harnessing the true power of crowd-sourcing. An ensemble model with outperform every single model, increasing overall profitability of the strategy - everyone wins by collaboration.The models will be vetted by rigorous backtesting and out of sample tests.

How do we reward users?

We charge investors a performance fee on the capital and reward our users by splitting this fee equally between the user and Auquan. The IP of the strategy will be owned by the creator of the strategy.

How are we implementing this?

Auquan has created a beginner tutorial series aimed at creating quants equipped with right knowledge, skills and attitude required to successfully write quantitative strategies. The tutorials require no prior financial knowledge and are divided into a series of lessons, with each one focusing on a different aspect of creating a data-driven trading algorithm, from finance basics and developing the idea for a quantitative trading strategy to modeling techniques, fine tuning a strategy, backtesting pitfalls, and strategy development best practices.

Auquan has a beginner's backtesting toolbox to help users with the development and the backtesting of trading algorithms. The toolbox and simple, extensible and easy to use. Auquan also provides clean historical data users will need to uncover patterns in the data, abstracting finance domain knowledge out of the problem.

Auquan conducts periodic competitions for users to test their skills against other participants and get their strategies notices by investors and trading firms. The strategies submitted by users are evaluated on performance and key risk metrics via paper trading. The contestants with the best performing algorithms at the end of paper trading period are rewarded.

Meet the Team

Auquan is empowered by a team of highly motivated individuals each of whom is a veteran of their respective industries.

Chandini Jain

Chandini Jain

Founder & CEO

Chandini Jain, founder - Auquan

Kanav Arora

Tech Advisor

Next Steps...

Get our free and open source backtesting toolbox