Democratizing & Simplifying Data Science For Financial Traders & Researchers

An intuitive software platform combining sophisticated machine learning with traditional trading strategies to discover more diverse and effective financial modeling

Bringing the power of data science & machine learning into your investment process

  • Complicated Technology
    Simple to use UI
  • High Costs
    Cost Effective Annual License
  • Knowledge gap
    Enhance Investment Strategies
Traditional Investing
  • Technical - moving averages, overbought/oversold
  • Fundamentals - P/E ratios, growth or value
  • Proprietary indicators
Traditional investing with machine learning
  • Bayesian algorithms, Random Forest
  • Correlation clusters
  • Genetic optimization
  • Continuous learning for regime changes
  • Rapid model building & testing
Traders, analysts, economists and other investment professionals across a range of investment types – including hedge funds, mutual funds and family offices – can now easily leverage the power of data science and machine learning without hiring large technical teams to build expensive, complex solutions.


It starts with a huge universe of possibilities, with as much data as needed and culminates by generating model predictions for live trading.

Providing the power of data science and machine learning with the ease of a point-and-click UI.

  • Step 1

    Step 1 Genetic Optimization FME (GOFME)

    A genetic algorithm takes a less granular look at the research process before theories are fine-tuned in the FME

    By sampling only a small percentage of the total universe, the user is able to identify key attributes for more granular research

    Step 1 Picture
  • Step 2

    Step 2 Financial Modeling Environment (FME)

    Perform massive simulations of futures and equity markets

    Distributed walk-forward simulation framework capable of running all possible combination of feature inputs on AWS or local servers and supports a wide range of machine learning algorithms

    Step 2 Picture
  • Step 3

    Step 3 Visualization & Correlation

    Display multiple markets, models, outputs and statistics to help in the research process

    Correlate markets, equity curves and prediction streams with user-defined time periods and metrics

    Step 3 Picture
  • Step 4

    Step 4 Clustering

    Use Markov Cluster Algorithm to group similar equity curves based on the correlation threshold

    Determine top-performing models from each cluster based on performance metrics that allows the user to pick a diverse set of optimal models

    Step 4 Picture
  • Step 5

    Step 5 Model Selection & Regime Change

    Automates the model selection process to determine exactly which markets and models to trade

    Ability to identify and react to Regime Changes

    Step 5 Picture
  • Step 6

    Step 6 Model Selection Framework

    Automated functionality to quickly make updates from research to production models in an efficient, seamless process.

    Step 6 Picture


VeridianML helped Blackwater Capital Management

increase its winning percentage on trades by 20%

By using VeridianML’s algorithms to analyze Blackwater’s rules-based system, research was taken to a new level.

Using multiple algorithms on the same problem helped Blackwater better understand results and drive more confidence in the value potential of a black box solution.

  • Jeff Austin

    Jeff Austin

    Founder, head of product development with 20+ years trading client capital in the global macro quantitative space. Jeff has spent his entire career focused on trading and model building. Found of Blackwater Capital Management, where he was the CIO and responsible for all model and portfolio construction, trading FX, futures, equities and ETFs.

  • Anatoli Likhachev

    Anatoli Likhachev

    SVP Quant Strategy & Research who is responsible for all aspects of product development, product integration and collaboration with partners. He has over 20 years of experience in areas of finance, information technology and automated trading systems. Anatoli received his B.S. and M.S. degrees both in Computer Science at McGill University in Montreal. He devoted his Master’s Thesis to developing automated trading systems using neural nets and genetic algorithms. He is also a charter holder of CFA, FRM, CAIA and CMT.

  • BabakAfhsin-Poor


    PHD is our SVP Technology who is responsible for streamlining the software architecture, managing the distributed computing environment and collaborating on machine learning and AI initiatives at VeridianML. Babak’s experience and interests are in the areas of big data analysis using Apache Spark, advanced signal and image processing, graph theoretical network analysis. Babak received a B.S., degree in biomedical engineering as well as his M.S. and PH.D. in electrical engineering from University of Tehran with distinction. He then was awarded a three-year post-doctoral fellowship at the Rotman Research Institute, University of Toronto.


Schedule a demo