John Muller
Verified Expert in Engineering
Analyst and Developer
Charlotte, NC, United States
Toptal member since September 4, 2020
John is a computer scientist, data scientist, finance quant, and creative problem solver. He loves the challenge of taking on real-world problems with algorithms, data structures, and professionally written code. John has a Ph.D. in computer science and over ten years of experience using R and Python and for modeling and visualization, and data manipulation. John is an effective communicator with both technical and business-oriented colleagues.
Portfolio
Experience
- R - 12 years
- Python - 11 years
- Algorithms - 10 years
- Data Analytics - 10 years
- Analytics - 10 years
- Quantitative Finance - 7 years
- Data Science - 6 years
- Data Visualization - 5 years
Availability
Preferred Environment
Linux, RStudio, PyCharm, Windows
The most amazing...
...project I've worked involved analyzing survey data from data scientists. We clustered the observations and were fascinated to see the natural groupings emerge.
Work Experience
Data Scientist
TIAA
- Classified customer feedback and automatically generated customer responses (NLP projects).
- Wrote code to optimize the cutoff threshold percentage for the classification service.
- Improved the classification service with clever model enhancements.
Data Scientist
Lowe's
- Applied Graph ML methods to create embeddings to be used for product recommendations.
- Wrote SQL queries to create rule-based recommendations.
- Applied hyperparameter optimization to improve ML algorithms.
Senior Analyst, Code Review Team
Large Consumer Bank
- Reviewed code (mostly Python and SQL) to determine if it accurately and completely met all documented requirements.
- Performed tests on the data and code to check for missing or unexpected values.
- Reran the original code and compared the output to the original output.
- Worked on projects that required a high level of skill in Python and SQL and occasionally R and even SAS; and often times requiring skill in and knowledge of Spark, Hadoop, and Hive.
VP, Portfolio Construction Group and Model Implementation Group
Acadian Asset Management
- Designed and built a dashboard for PMs to analyze portfolio exposures within and across strategies.
- Developed code to add transaction costs to our attribution and a web app (Bokeh) for exploring the results.
- Built an automatic testing program to run simple pass/fail tests on code where no explicit test code exists. Used Python’s introspection to find methods and method signatures to assign valid values for arguments.
- Worked on other projects including an investment strategy capacity analysis, rebalancing a schedule frequency analysis, a ranking of broker performance, an FX hedge reporting module, an access layer to alpha model data, and more.
Lead Data Scientist
EnterTheData
- Estimated the value of a marketing campaign vis-à-vis resulting sales using a time series analysis,.
- Analyzed customer retention using survival analysis to find differences across markets.
- Predicted government employment releases using lasso regression and random forests.
VP, Head of Analytics and Visualization
State Street Associates
- Led a collaboration between research and the securities lending business to build analytic tools to support trading.
- Worked on analysis and modeling projects including predicting hard-to-borrow securities and analyzing the relationship between real and synthetic shorts using options.
- Led a team for new holdings indicators, i.e., a trading signal for equity and fixed income.
- Managed teams that developed and released 14 new foreign exchange and equity flow indicators.
Senior Vice President
Bank of America
- Coded (using R) and back tested various improvements to the existing momentum-style strategy drawing data from MarketQA, IDC, IBES, and Compustat.
- Provided quantitative support for users of Barra’s Enterprise Performance product for return attribution.
- Designed and coded fixed income tools using R and C++.
- Developed code to calculate generic yield curves and bond asset swap spreads.
- Conducted an extensive analysis of the customer database and provided analytic research on the effects of pricing policies to support the mortgage pricing team.
Experience
Exploratory Data Analysis of Survey Data
It was fascinating to see the natural groupings emerge from the data. For example, there was a group that did mostly data manipulation and extraction, a modeling group, a visualization group that seemed to mostly interact with the business side.
Data Science/Machine Learning Projects
http://github.com/jhmuller/jhmuller.github.ioPlease have a look. I am adding new projects frequently.
Education
Ph.D. in Information and Computer Science
Georgia Institute of Technology - Atlanta, GA, United States
Certifications
Certificate in Quantitative Finance
Carnegie Mellon
Skills
Libraries/APIs
Pandas, PySpark, NumPy
Tools
PyCharm, StatsModels, MATLAB, Spotfire
Languages
Python, R, SQL, C++, Java, Python 3
Frameworks
Spark, Hadoop
Platforms
Windows, RStudio, Linux, Docker
Storage
Apache Hive
Other
Graph Theory, Algorithms, Quantitative Finance, Analytics, Data Visualization, Data Science, Data Analytics, Regression, Regression Modeling, Data Analysis, Statistical Modeling, Data Structures, Calculus, Numerical Methods, Derivatives, Google BigQuery, Graph Machine Learning, Machine Learning, Artificial Intelligence (AI)
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring