Druce Vertes, Machine Learning Developer in New York, NY, United States
Druce Vertes

Machine Learning Developer in New York, NY, United States

Member since September 23, 2019
Druce has a career that spans decades, and during that time he's worn many hats. Recently, he's been consulting on projects involving machine learning, alternative data, predictive analytics (Python, Sklearn, Keras, and TensorFlow). He's also worked as a quantitative analyst, IT manager, and developer with leading hedge funds and Wall Street firms and even served for three years a the CTO of a $2 billion long/short-equity hedge fund.
Druce is now available for hire




New York, NY, United States



Preferred Environment

Scikit-learn, Jupyter, GitHub, PyCharm, Windows, Ubuntu

The most amazing...

...project I've worked on was a retirement investment allocation and spending glide path to maximize certainty-equivalent spending.


  • Machine Learning Developer and Consultant

    2011 - PRESENT
    Independent Consultant (StreetEYE, LLC)
    • Developed a web news aggregator/algorithmic news feed for financial market news using machine learning (Keras, Sklearn. NLTK) for StreetEYE.com.
    • Consulted on the development of machine learning and alternative data projects for a top-tier hedge fund (using Sklearn, Keras, and DataRobot).
    • Wrote on financial market topics for the following publications: Alpha Architect, AAII Journal, CFA Inside Investing, ValueWalk, Seeking Alpha, Huffington Post, Benzinga, and Steadfast Capital.
    • Consulted on the development of machine learning and alternative data projects using Sklearn, Keras, and DataRobot.
    Technologies: TensorFlow, Keras, Scikit-learn, R, Pandas, Python, NumPy
  • Chief Technology Officer

    2008 - 2010
    Hoplite Capital Management
    • Implemented the IT infrastructure including the network, Bloomberg, disaster recovery, remote access via Citrix and VPN, mobile device management, and telecoms (Avaya).
    • Brought workflows and policies up to industry best practice—emphasizing efficient workflows, disaster recovery, and cybersecurity.
    • Developed real-­time P&L spreadsheet, attribution, portfolio analytics, ETL workflows.
    • Managed Eze Castle order management system, security, master/reference data, FIX electronic trading, compliance, Oasys post­trade matching, internal workflows, and interfaces with external service providers.
    • Supported third­-party software for research content management (Tamale), accounting (SS&C Advisorware), investor relations (PerTrac CMS), and Microsoft Office.
    Technologies: MDM, BlackBerry, Microsoft 365, Content Management Systems (CMS), Citrix, Castle, Bloomberg, SQL, Excel VBA
  • Implementation Manager

    2005 - 2007
    Charles River Development
    • Led the implementations of Charles River IMS for major hedge funds.
    • Conducted a requirements analysis.
    • Created a workflow design.
    • Implemented and configured a trading system.
    • Performed unit and parallel testing.
    • Trained, managed the project, and provided trading support and troubleshooting.
    • Re-engineered various workflows including trading desk (blotter, FIX electronic trading), portfolio analytics, performance measurement/attribution, and compliance.
    Technologies: Investments & Risk Management
  • Independent Software Development Consultant Focused on Financial Markets, Trading, and Hedge Funds

    1995 - 2005
    Consulting Work
    • Acted as the interim CTO for CF Global Trading.
    • Managed the development of the web presence for the leading multi­dealer FX trading startup, FX Alliance, LLC.
    • Oversaw the development of the web presence/CMS for FX research sales and trading for Goldman Sachs.
    • Generated analytics and reporting for hedge fund clients on behalf of Morgan Stanley.
    Technologies: Adobe ColdFusion, Perl, Web Development, Python
  • Analyst

    1993 - 1994
    Caxton Corporation
    • Worked as a developer and quantitative analyst for a leading macro hedge fund.
    • Implemented databases of economic time­series and corporate fundamentals in major global markets in FAME.
    • Developed portfolio analytics in FAME, Perl, and Excel.
    • Identified country and sector trading ideas using proprietary analytical tools.
    Technologies: Microsoft Excel, Perl, Banking & Finance
  • Developer and Analyst

    1991 - 1992
    Tiger Management Corporation
    • Developed a trading system for equities, fixed income, derivatives trades using C++, UIM/X, and Informix DB.
    • Built Tiger's first real­-time P&L spreadsheet.
    Technologies: IBM Informix, SQL, C++
  • Quantitative Research Analyst

    1986 - 1991
    Salomon Brothers, Inc.
    • Developed software to construct optimized equity portfolios using Salomon’s proprietary multi­factor risk attribute model.
    • Implemented analytics to estimate stock portfolio volatility, tracking error vs. market indexes, and correlation to fundamental factors including inflation and interest rates.
    • Performed portfolio optimization using linear and quadratic programming.
    • Worked with institutional clients to structure optimized portfolios.
    • Worked initially as an economics analyst and created statistical models and forecasts of economic indicators (CPI, PPI, leading indicators) using FAME and spreadsheets.
    • Wrote internal and external research reports; gave real-time analysis to traders and clients on economic releases.
    Technologies: C, Banking & Finance


  • Optimal Retirement Planning Using Certainty-equivalent Spending

    Using various global optimizers, I computed the universe of stock/bond allocations and spending rules to find the plan that would historically have maximized certainty-equivalent spending at various levels of risk aversion. I then created a visualization using React, allowing users to explore optimal rules and the historical spending patterns they would have supported.

    Historically, what would have been the optimal allocation and spending plan for retirement?

    If you are maximally risk-averse, the Bengen 4% rule holds up: start by spending 4% of your portfolio and increase annually for inflation. If you are less risk-averse, a more flexible rule like a fixed spending amount plus a percentage of assets might make more sense.

    Longer writeup: https://www.advisorperspectives.com/articles/2021/03/22/beyond-the-4-rule-flexible-withdrawal-strategies-using-certainty-equivalent-spending

  • Portfolio optimization with cvxpy

    A tutorial on portfolio optimization using mean/variance analysis with cvxpy. For different risk tolerance levels, what is the optimal portfolio allocation between stocks, bonds, cash, and gold? I explored why we do mean-variance analysis, how we can use convex optimization and cvxpy to determine what optimal portfolios would have looked like over various historical periods and whether gold has a place in optimal portfolios.

  • StreetEYE Financial News Aggregator

    I built an algorithmic news feed for financial market news. I used the Twitter API, Pagerank, and NLP to rank the most influential accounts focused on financial markets and aggregate the news stories they shared. The public version is offline, but a demo is available on request.

  • Alpha Architect Post: Factor Investing with Machine Learning

    An overview of machine learning classification methods and application to a factor investing problem by attempting to forecast future performance quantiles. While seemingly quite successful, the result seems to demonstrate overfitting, and regression and learn-to-rank outperform vanilla multinomial classification with softmax loss.

  • Risk Arbitrage: Investing and Poker

    I wrote a blog post exploring analogies between investing and playing the game of poker. Both are games of quantitative thinking about imperfect information and psychology. But real-world markets don't reward bluffers.

  • Active vs. Passive Investing and the “Suckers at the Poker Table” Fallacy

    This is a thought experiment on what would happen if more and more people invest passively. There's no such thing as a 100% purely passive investor: we are free to pick a strategy but not avoiding the choice. As more people invest more passively, they save on expenses, but market efficiency decreases. The ideal "Warren Buffett" active investor can always exploit any "suckers." At some point, though, the less active investing there is, the more excellent opportunities there are for remaining active investors to exploit.

  • Alpha Architect Post: Deep Reinforcement Learning for Trading

    An overview of deep reinforcement learning, code examples with OpenAI gym Cartpole and LunarLander, and code to implement policy gradient on market data, with positive results on simulated data (Ornstein–Uhlenbeck mean reversion process and noise).

  • Quantitative Fun with Fund Names

    Here on a blog post, I had fun with topic modeling, clustering, Word2vec, and text generation with fund names. A recurrent neural network trained on a corpus of fund names generates new fund names based on any starting letters.

  • The Mathematics of Bluffing

    Used Mathematica to explore optimal bluffing frequencies and call frequencies in poker based on simplified assumptions. As long as you have a positive EV to bluffing, you should increase your bluff frequency. There is a Nash equilibrium where the EV to bluffing more frequently and calling more frequently are 0.

  • Pizza Pizza Pizza

    A platform that allows users to search on Google Maps, Yelp, and Foursquare for a keyword like 'Pizza' displays a combined Bayesian ranking and results on a map.

    Back-end stack: Python, Flask, deployed as a Docker microservice in Amazon ECS.

    Front-end stack: Bootstrap, jQuery, Leaflet.js.


  • Languages

    Python, Python 2, Python 3, Excel VBA, R, JavaScript, SQL, Visual Basic for Applications (VBA), Java, C++, C, HTML5, CSS3, Perl, Snowflake
  • Other

    Markets, Deep Reinforcement Learning, Artificial Intelligence (AI), Machine Learning, Deep Learning, Predictive Analytics, Data Visualization, Content Management Systems (CMS), Microsoft 365, MDM, Investments & Risk Management, Web Development, AWS, Finance, Computer Science, Logistic Regression, Neural Networks, Linear Regression, Generalized Linear Model (GLM), Recurrent Neural Networks, Convolutional Neural Networks, Clustering, Natural Language Processing (NLP), Optimization, Equity Index Quantitative Analysis, Indexing, Portfolio Analysis
  • Frameworks

    Django, Bootstrap
  • Libraries/APIs

    Scikit-learn, Keras, TensorFlow, XGBoost, jQuery, NumPy, SciPy, Pandas, Plotly.js, Matplotlib, React
  • Tools

    Seaborn, GitHub, Jupyter, Bloomberg, Adobe ColdFusion, Microsoft Excel, Amazon SageMaker, MATLAB, Mathematica, PyCharm
  • Paradigms

    Data Science, Object-oriented Programming (OOP), Functional Programming
  • Storage

    Relational Databases, IBM Informix, MySQL, PostgreSQL, SQL Server 2008
  • Platforms

    Ubuntu, Windows, Citrix, BlackBerry, Amazon Web Services (AWS), Jupyter Notebook, Amazon EC2
  • Industry Expertise

    Banking & Finance


  • Bachelor's Degree in Computer Science
    1982 - 1986
    Columbia College - New York, NY, USA


  • Snowflake Hands On Essentials - Data Warehouse
    MARCH 2022 - PRESENT
  • CFA Charter
    JANUARY 2010 - DECEMBER 2019
    CFA Institute

To view more profiles

Join Toptal
Share it with others