Tal Sansani is a technologist, quantitative researcher, and investment management consultant with over 15 years of professional experience. Prior to consulting, Tal built and led the data-science efforts at American Century Investments' Quantitative Equity Group, directly informing investment strategies of nearly $15B in AUM.
Tal operates at the intersection of technology and investment research: with extensive hands-on experience developing unstructured data pipelines, performance analytics, and predictive financial models. His practical investment applications of Natural Language Processing (NLP) and Machine-Learning have earned him recognition from industry leading organizations and the financial media. Tal graduated with honors from the University of California, Los Angeles, earning a B.S. in Applied Mathematics, with a Specialization in Computing. He is a CFA Charterholder.
Away from work, you'll find Tal in Oakland, CA, spending time with his wife and two kids, riding his bike, pickleballing, golfing, and overly obsessing about NBA basketball. 💻📈🎮🎨🌱🏀🏌🚴
In collaboration with Two Centuries Investments, Tal is actively quantifying corporate culture — from toxicity to creativity — across thousands of publicaly traded companies. Applying Natural Language Processing (NLP) to volumes of text, we provide behind-the-curtain, valuation-relevant insights to investors. You can learn more about what we're doing @ cultureline.ai
Moving from a career in the corporate world to consulting allows me to more purposfully align the things I do with the things I like. "My work" often looks something like this:
Managing Messy Data
Data-Driven Research & Development
Making it Practically Useful for Others
Focusing on what I like is both clarifying and effective. Free from layers of corporate bureaucracy, I now connect more directly with the people I'm helping and the problems I'm solving, ultimately leading to more creative and meaningful outcomes.
My focus is quantitative research, which combines data and economic sensibilities to better understand why some companies succeed and others fail. I am specifically interested in the quantification of company intangibles (culture, brand, intellectual property, human capital, etc.) and a variety of other hard-to-pin-down dimensions (investor sentiment, economic moats, environmental impact, etc.) that aren't neatly published in financial statements.
Favorite Research Topics:
Favorite Data Sources:
Hands-on experience implementing production data-pipelines, stock-selection models, and custom research applications. Combining modern frameworks with cloud infrastructure, favoring simplicity over complexity.
Institutional experience building stock-selection models, leading data-science teams, and managing portfolios. CFA Charterholder. Combining economic intuition with non-traditional data, favoring simplicity over complexity.