Robert Roloff, Developer in Munich, Bavaria, Germany
Robert is available for hire
Hire Robert

Robert Roloff

Verified Expert  in Engineering

Data Scientist and Machine Learning Developer

Location
Munich, Bavaria, Germany
Toptal Member Since
October 14, 2021

Robert is a data scientist and quantitative researcher with an extensive background in time series forecasting and quantitative finance. He has applied various machine learning techniques to predict the global futures, stock, and ETF markets. Robert is looking for projects that allow him to use data and machine learning to solve complex problems. Machine learning is not only part of Robert's professional portfolio but also his hobby.

Portfolio

Amfileon AG
Quantitative Finance, Python, Trading, Futures & Options, Equities...
Freelance
Quantitative Modeling, Time Series Analysis, Forecasting, Python...
QuantRes Asset Management
Python, Quantitative Finance, Time Series Analysis, Data Science, Forecasting...

Experience

Availability

Part-time

Preferred Environment

Python, PyCharm, RStudio, Linux, R

The most amazing...

...project I've done was to research and implement new machine learning methods for the trading strategies of a quantitative asset manager.

Work Experience

Quantitative Portfolio Manager

2021 - 2023
Amfileon AG
  • Researched and implemented market-neutral intraday equity trading strategies.
  • Developed data pipelines for intraday futures and options data.
  • Handled various components of Amfileon's trading infrastructure: backtesting system, compliance checks for the UCITS fund, order management system, and trading interfaces to MTFs like FXall and Tradeweb.
Technologies: Quantitative Finance, Python, Trading, Futures & Options, Equities, Machine Learning, Portfolio Analysis, Statistics, Data Science, Data Engineering, Time Series Analysis, Forecasting, GitLab, Pandas, NumPy, H2O Deep Learning Platform, SQL, Git, Data Scientist, Quantitative Modeling

Data Scientist | Quantitative Researcher

2020 - 2021
Freelance
  • Implemented prototype models for gas and electricity demand predictions.
  • Developed machine learning models to forecast commodity spot prices and volatilities.
  • Researched leading macroeconomic and technical indicators to be used in forecasting models.
Technologies: Quantitative Modeling, Time Series Analysis, Forecasting, Python, Machine Learning, Data Science, Commodities, Utilities, Futures, Pandas, NumPy, H2O Deep Learning Platform

Quantitative Researcher (Freelance)

2015 - 2019
QuantRes Asset Management
  • Initiated, led, and contributed to a project for a machine learning-based trading strategy; the client uses the solution for his main fund.
  • Created cloud-based hyperparameter optimization infrastructure for machine learning models, supporting Bayesian, random, and grid search.
  • Applied statistical methods to detect structural breaks in financial data.
  • Handled time series cross-validation methods for a backtesting system.
  • Developed R and Python back ends for machine learning model training.
  • Moved the client's machine learning infrastructure to the cloud—AWS EC2— and developed an API that handles the AWS cluster management.
  • Created prototype models using random forests, gradient-boosted trees, and neural networks for time series forecasting.
Technologies: Python, Quantitative Finance, Time Series Analysis, Data Science, Forecasting, R, Amazon Web Services (AWS), Optimization, Futures, Machine Learning, Bloomberg, Boto 3, H2O Deep Learning Platform, NumPy, SQL, Git, Subversion (SVN), Quantitative Modeling

Quantitative Researcher

2013 - 2015
QuantRes Asset Management
  • Developed quantitative trading strategies for various markets such as S&P 500, Russell 2000 Universe, Futures, FX, and ETFs.
  • Researched, implemented, and managed two proprietary trading strategies.
  • Tested trading ideas sourced from academic literature.
Technologies: Python, Quantitative Finance, R, Stock Market, Futures, Trading, Machine Learning, Data Science, Bloomberg, Pandas, SQL, Dplyr, Git, Subversion (SVN), Quantitative Modeling, Optimization

Quantitative Risk Analyst

2010 - 2013
Raiffeisen Capital Management
  • Calculated risk measures for several equity and derivatives portfolios.
  • Presented portfolio-relevant key figures and statistics to funds and senior management.
  • Performed pre-trade analysis for the trading desk to ensure compliance with risk limits.
Technologies: R, Market Risk, Bloomberg, Quantitative Finance, Value at Risk, Derivatives, Stock Market, Dplyr, SQL, Quantitative Modeling, Optimization

New Machine Learning Methods for an Existing Trading System

Based on an obfuscated data set provided by the client, a quantitative asset manager, I researched whether new machine learning methods could improve the existing trading systems. Since the outcome of the initial research project had been very promising, the client decided to use the new approach in production. In the following steps, I prepared a roadmap for the implementation, and we gathered a team of other researchers and developers. Together with a freelance developer, I created a new machine learning back end that allowed us to leverage cloud computing resources from AWS. The solution is now successfully used by the client for the trading strategy of his main fund.

Cloud-based Hyperparameter Optimization Infrastructure

Training machine learning models for financial time series data often requires specific cross-validation schemes that standard libraries, such as scikit-learn, do not support. I developed a hyperparameter optimization infrastructure including Bayesian, random, and grid search that takes the client's cross-validation schemes into account and uses cloud computing resources from AWS. This enabled the client to search a much larger parameter space and train better machine learning models for his trading strategies.

Commodity Spot Price and Volatility Forecasting

Recently, commodity prices have become increasingly volatile, and sometimes they show very strong trends. As a consequence, producers and consumers of these commodities seek ways to optimize their hedging against adverse price movements. The client I was working for provides software that generates price and volatility predictions for commodities via modern machine learning tools. I researched and developed several models for a range of industrial and precious metals, allowing the client to extend their product universe.

Languages

Python, R, SQL

Libraries/APIs

Pandas, Scikit-learn, NumPy, SQLAlchemy, XGBoost, SciPy, Rcpp, PyTorch, Keras

Paradigms

Data Science

Platforms

H2O Deep Learning Platform, Amazon Web Services (AWS)

Other

Quantitative Finance, Machine Learning, Time Series Analysis, Forecasting, Quantitative Modeling, Futures, Stock Market, Trading, Derivatives, Optimization, Market Risk, Value at Risk, Futures & Options, Equities, Portfolio Analysis, Statistics, Data Engineering, Commodities, Utilities, Data Scientist

Tools

Dplyr, Boto 3, Git, Subversion (SVN), Bloomberg, GitLab

Storage

PostgreSQL

2007 - 2010

PhD in Physics

University of Graz - Graz, Austria

2001 - 2007

Master's Degree in Physics

University of Graz - Graz, Austria

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring