Christopher is available for hire
Hire ChristopherChristopher Bukowski
Verified Expert in Engineering
Data Scientist and Developer
Denver, CO, United States
Toptal member since March 31, 2020
Bio
Chris is a data scientist with a decade of experience split between academic and professional settings. He specializes in creating predictive models to solve unique and interesting problems. He uses his knowledge and expertise to provide data driven guidance that enables businesses to grow and advance. Freelancing allows him to expand his knowledge and work on challenging and unique problems in varied domains.
Portfolio
Nyumbics
Python 3, TypeScript, Consulting, Agile Project Management, Roadmaps, SaaS...
Ninja Holdings
Python 3, Kubernetes, Machine Learning, Data Science, Credit Risk...
The Energy Authority
Deep Neural Networks (DNNs), Deep Learning, Data Modeling, Customer Data...
Experience
- Statistics - 12 years
- R - 12 years
- Data Visualization - 10 years
- Data Analytics - 8 years
- Data Science - 8 years
- Python 3 - 6 years
- Machine Learning - 6 years
Availability
Part-time
Preferred Environment
Python, R
The most amazing...
...model I've created accurately forecasted the price of electricity up to a week in advance and produced annual returns of over 200%.
Work Experience
Co-founder
2023 - PRESENT
Nyumbics
- Developed an app that harnesses the power of ChatGPT to make AI accessible to real estate professionals. This app not only uses ChatGPT to create content but integrates data from other sources to provide richer context.
- Created a business to sell data science as a subscription service. This business model is a new way to access and interact with senior talent.
- Took an idea from conception through MVP and into production. Marketed and sold the product through relevant industry avenues.
- Designed, engineered, and published a suite of tools aimed at empowering job seekers. The products use a variety of Python libraries like LangChain and Streamlit to leverage custom and existing LLM APIs to fulfill user requests.
Technologies: Python 3, TypeScript, Consulting, Agile Project Management, Roadmaps, SaaS, Large Language Models (LLMs), Generative Artificial Intelligence (GenAI), Natural Language Processing (NLP), OpenAI GPT-4 API, OpenAI, Language Models, Generative Pre-trained Transformers (GPT), Machine Learning, Deep Learning, Predictive Modeling, Real Estate, Data Science, SQL, Data Analysis, Product Management, Data Science Product Manager, Statistical Modeling, Technical Leadership, Leadership, Mentorship & Coaching, Forecasting, Pandas
Senior Data Scientist
2021 - 2023
Ninja Holdings
- Developed and deployed a model to predict a customer's income based on initial credit bureau data. By making the prediction before requiring additional information, we reduced friction and churn throughout the underwriting process.
- Built cashflow models and forecasting tools to accurately predict customer repayments.
- Led the transition to Kubernetes from a data science perspective, orchestrating models into models as code and providing configuration assets for deployment in Kubernetes clusters.
Technologies: Python 3, Kubernetes, Machine Learning, Data Science, Credit Risk, Credit Scores, Risk Models, Credit Underwriting, Data Analytics, Business Analysis, Amazon SageMaker, Jira, Finance, Regression Modeling, Regression, Financial Modeling, Natural Language Processing (NLP), Azure Machine Learning, Predictive Modeling, Trend Analysis, Kubeflow, SQL, Data Analysis, Product Management, Data Science Product Manager, Statistical Modeling, Technical Leadership, Leadership, Mentorship & Coaching, Forecasting, Pandas
Data Scientist
2020 - 2021
The Energy Authority
- Developed an algorithm to detect broken and defective meters based on usage patterns, saving our clients millions of dollars in lost revenue each year.
- Successfully managed multiple projects across multiple clients, from requirements gathering through final product delivery.
- Implemented deep learning neural nets to predict customer behavior and automatically identify specific usage characteristics, which saved our clients millions in maintenance costs while increasing customer satisfaction.
Technologies: Deep Neural Networks (DNNs), Deep Learning, Data Modeling, Customer Data, Time Series Analysis, Sensor Data, Clients, Project Management, Data Science, Azure DevOps, SQL, Microsoft Power BI, Microsoft Azure, Databricks, Python 3, R, Regression Modeling, Trading, Regression, Azure Machine Learning, Neural Networks, Machine Learning, Predictive Modeling, Trend Analysis, Real Estate, Energy Management, Data Analysis, Product Management, Data Science Product Manager, Statistical Modeling, Technical Leadership, Leadership, Mentorship & Coaching, Time Series, Forecasting, Pandas
Senior Data Scientist
2012 - 2019
MWD Trading, LLC
- Created models to predict price movements in highly liquid commodities, futures, and power markets, which consistently produced returns in excess of 75% annually.
- Implemented and maintained all internal reporting for business and trade development, including deploying and managing an internal website which provided on-demand reporting using the R Shiny platform.
- Managed financial risks associated with commodities and futures positions held by the firm across all markets and exchanges.
- Developed programs and processes to reduce human evaluation of data and quantify subjective analysis.
- Worked closely with management to provide analysis and data-driven recommendations for business growth and development.
Technologies: Scala, Microsoft Excel, Java, Python, R, Finance, Regression Modeling, High-frequency Trading (HFT), Trading, Currency Exchange, Backtesting Trading Strategies, Regression, Financial Modeling, Natural Language Processing (NLP), Neural Networks, Machine Learning, Predictive Modeling, Trend Analysis, Data Science, Energy Management, Data Analysis, Statistical Modeling, Technical Leadership, Leadership, Time Series, Forecasting, Pandas
Teaching Fellow
2010 - 2012
Colorado School of Mines
- Developed curriculum for and implemented graduate-level statistical computing course taught to incoming graduate students.
- Constructed and taught undergraduate statistics courses focusing on theory and application of traditional statistical techniques and the technologies used to implement them.
- Worked in a team environment to define teaching objectives for undergraduate statistics courses.
Technologies: LaTeX, Linux, SAS, Minitab, MATLAB, R, Regression Modeling, Regression, Statistical Modeling, Mentorship & Coaching
Experience
AI Assistant for Real Estate Agents
http://www.agentis.comA project to make AI tooling more accessible to real estate agents. I developed an application using Next.js on the front end and Python for the back end. Also, I integrated ChatGPT to respond automatically to requests from agents through either the web application or an email interface. The email interface allows users to access full functionality without navigating to new web pages or applications. I worked on the entire project, from ideation to development through marketing and business development.
Interview Prep Tool
http://www.interviewprep.workA Python-powered application to help job seekers better prepare for interviews. The Streamlit interface allows users to upload a resume and job description and receive a list of interview questions. I was involved in every facet of this project, from ideation to launch.
Cover Letter Writer
http://www.coverletters.workA Python and Streamlit-powered application to help job seekers write a cover letter. By uploading a resume and job description, the user can select the style they would like the letter written in, and our back end uses ChatGPT APIs to fulfill the request. I was solely responsible for all development and marketing of the application. I managed this project from idea to launch.
Power Market Price Prediction
The goal of this project was to accurately predict day ahead and real time prices in various power markets. Prices were predicted one day to one week into the future. It employed machine learning techniques taking into account the temporal nature of power data. Data was aggregated from various sources (ISOs, weather data, ICE market data) to create the final model. The project led to a pricing model that accurately forecasted market prices, producing annual returns of around 200%.
High-frequency Trading (HFT) Strategy
This was a strategy that could be used to market make highly liquid commodities and futures markets. It focused on market microstructure to inform the model and make forecasts.
I was in charge of building and testing the model that was used to predict price movements over the next second. The general framework for this strategy was used to create models for over 20 different markets. In its more than six years in production, it consistently produced annual returns greater than 75%.
I was in charge of building and testing the model that was used to predict price movements over the next second. The general framework for this strategy was used to create models for over 20 different markets. In its more than six years in production, it consistently produced annual returns greater than 75%.
Power Load Curve Classification
The project involved creating a script to automatically classify load forecasts for various power markets. Load forecasting is an integral park of any price model in power markets, and as such, correctly classifying the type of curve is crucial. Accurately classifying the shape of the curve was done to remove any human subjectivity and aid in automating manual processes.
Reporting Web Page
This was a web page that provided on-demand reporting about all current and past trading strategies. I was in charge of building and maintaining this site. The site was built using the R-Shiny platform. It provided users a quick look at any trading strategy over the previous six months. Through a series of widgets and dashboards, it allowed users to quickly monitor business and trade performance and make data driven decisions going forward.
Machine Learning Model to Process Insurance Claims
I built machine learning models to automatically classify and detect fraudulent or overcharged insurance claims. Also, I created models and provided explanations for publication in research articles. Using Python, I was able to successfully classify anomalous insurance claims for a national healthcare system.
Education
2010 - 2012
Master's Degree in Applied Mathematics and Statistics
Colorado School of Mines - Golden, CO
2007 - 2010
Bachelor's Degree in Statistics
Colorado School of Mines - Golden, CO
Certifications
MAY 2020 - MAY 2026
Certified Analytics Professional (CAP)
INFORMS
JANUARY 2020 - PRESENT
Project Management Certificate
Cornell University
Skills
Libraries/APIs
Pandas
Tools
Microsoft Excel, MATLAB, LaTeX, Microsoft Power BI, Azure DevOps Services, Amazon SageMaker, Jira, ChatGPT, Azure Machine Learning
Languages
Python, Python 3, R, SQL, SAS, Java, Scala, TypeScript
Platforms
RStudio, Databricks, Jupyter Notebook, Azure, Linux, Kubernetes, Docker, Kubeflow
Frameworks
RStudio Shiny, Next.js
Storage
PostgreSQL
Industry Expertise
Project Management, High-frequency Trading (HFT)
Paradigms
Azure DevOps, ETL, Agile Project Management
Other
Data Analysis, Statistical Analysis, Data Science, Data Visualization, Machine Learning, Data Analytics, Statistics, Commodity Trading & Risk Management (CTRM), Finance, Regression Modeling, Regression, Large Language Models (LLMs), Project Scoping, OpenAI GPT-4 API, OpenAI, Language Models, Predictive Modeling, Statistical Modeling, Time Series, Forecasting, Deep Learning, Profit & Loss (P&L), Financial Data Analytics, Trading, Currency Exchange, Backtesting Trading Strategies, Financial Modeling, Artificial Intelligence (AI), Generative Artificial Intelligence (GenAI), Natural Language Processing (NLP), Software Project Management, Generative Pre-trained Transformers (GPT), Neural Networks, Trend Analysis, Real Estate, Energy Management, Product Management, Data Science Product Manager, Technical Leadership, Leadership, Mentorship & Coaching, Retrieval-augmented Generation (RAG), LangChain, Minitab, Microsoft Azure, Clients, Sensor Data, Time Series Analysis, Customer Data, Data Modeling, Deep Neural Networks (DNNs), Credit Risk, Credit Scores, Risk Models, Credit Underwriting, Business Analysis, Consulting, Roadmaps, SaaS, APIs, Business Development, Development, Marketing Mix, Software, Supervised Learning, Unsupervised Learning
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