How Lucena Designs Winning Strategies using Predictive Analytics

View each installment in our three part series.
The formation of a profitable quantitative trading strategy is a unique intellectual undertaking that draws on out-of- the-box thinking, perseverance, proprietary data, and nearly all aspects of computer science. The challenge is amplified when we custom build a strategy inspired from an investment book or a client’s mandate.

Our goal in this presentation is to take you on a creative journey from the seed of an investment idea to a live systematic traded strategy. Finding real value in algorithmic trading requires a self-adjusting protocol that constantly responds to changes in the market while constantly avoiding the trap of overfitting.

Meet our lead quants as they carry you through our regimented engagement process designed to service a fast-growing market of do-it- yourself investors. From identifying relevant data, applying cross validation through parametric searches, implementing machine learning algorithms, back-testing, paper trading, and all the way to live deployment. You will see first-hand how we have made custom investment strategies more accessible through automation. We let the machine paint the picture with broad strokes and then our quants follow up with meticulous handcrafted fine tuning for optimal solutions.

Part I: Initial Research

  • Assessing a data source
  • Introduction to Event Analysis
  • Identifying predictive data with the Analyzer
  • Using predictive analytics to discover additional factors for a model
  • Q&A with our quants.

Part II: Backtesting an Event

  • Event backtest settings & parameters
  • How settings affect performance
  • In sample and out of sample analysis
  • Q&A with our quants.

Part III: Test and Deployment

    • Cross-validation through parametric search
    • Paper trading
    • Live deployment
    • Q&A with our quants.

 

Tucker Balch, Ph.D. is a former F-15 pilot, professor at Georgia Tech, and co-founder and CTO of Lucena Research, an investment software startup. His research focuses on topics that range from the understanding social animal behavior to the challenges of applying Machine Learning to Finance. His online course, Computational Investing Part I, is the most popular online course offered by Georgia Tech and one of the most popular at coursera.com with over 175,000 students enrolled. Balch holds B.S. and Ph.D. degrees in Computer Science from Georgia Tech. Honors include the NSF CAREER Award, the Georgia Tech Outstanding Service Award and a distinguished graduate designation from the USAF in Undergraduate Pilot Training. Tucker has authored over 150 technical papers, journal articles and books, including the recent book What Hedge Funds Really Do with Philip Romero. His work has been reported in the popular press and TV including on CNN, in Institutional Investor, the New York Times and the New Scientist.

Erez Katz is an accomplished serial entrepreneur and a C-level executive with a proven track record of effective leadership, instilling operation efficiencies and driving profitable growth. Erez is the active CEO and Co-Founder of Lucena research and was instrumental in architecting and designing Lucena’s flagship product QuantDesk®. Today, Erez shares his expertise in applying Lucena’s technology to help investment professionals generate Alpha, minimize risk via portfolio optimization and construct new portfolios using predictive analytics and machine learning technology. Prior to co-founding Lucena with Dr. Tucker Balch, Erez was the founder of Objectware Inc, a web technology company, which was sold in 2007 to Bridgeline Digital. Erez was instrumental in growing Bridgeline and in its transition to the public domain on Nasdaq. Erez also assumed Bridgeline’s Chief Operating Officer through 2011.