DATA Projects

As a creative type, I almost always have many irons in the fire. As such, I regard all projects as in process and am always circling back to add another feature or retest them for bugs. Below you will see a list of what I have as well as what I am working on. In some cases, if I feel something is polished enough to share, I have included a hyperlink to the file itself. In other cases, the project is either too green or the data is protected. If you like what you see, have an idea for an improvement, or are interested in commissioning a project please contact me. I always appreciate feedback.

Data Science: University of Idaho Foundation

Current Work
  • Graph shows minimal detectable effect of an AB test as a function of response rate for a given sample size.
  • Lower curve shows percentage of base population.
  • Discontinuous green curve shows whole number of values needed to reach minimal detectable effect.
  • This is an example of current statistical work using mock data

Data Science and Dashboard: Archer Strategic Advisors

Sping 2024
  • I created a Microsoft Excel impact calculator for the Research and Development tax credit, allowing for informed decision making.
  • The calculator includes a 5-stage binary logic tree for qualification requirements relative to different sub-options and elections in order to quickly compare and select the variation of maximal benefit.
  • It also includes a fixed-base percent calculation which involves ratios of running averages of R&D expenses to gross receipts for specific years up to 40 prior tax years.
black framed eyeglasses and black pen
black framed eyeglasses and black pen

Data Science and Dashboard: Mock data and presentation for University of Idaho

Sping 2024
  • I created a Python code analysis of a mock data set regarding donations to the U of I over a five-year period.
  • The dashboard allows for quick comparisons between different donor segmentaion options.
  • It also includes a PowerPoint presentation intended for stakeholders to recommend future financial strategies for the institution.
  • The full presentation can be viewed here

Data Science: North Idaho College Math Education Center

Sping 2024
This is a Python performance model. I wrote Python code to integrate tutor log data with gradebook data for the Math Education Center providing actionable output. I built an ETL pipeline from CSV to Excel via Python data tools (Pandas, Matplotlib, scikit-learn, plotly…) I ran the cleaned, merged data through ML models to analyze the impact of tutoring on final grades. I created a dashboard in Power Bi and presented division-level stats for the program review. Further exploratory data analysis is currently in progress.
Insight includes:
  • Year-over-year compairision of usage adjusted for enrollment size.
  • Dailly usage versus staffing rates
  • Usage patterns within a semester for budget planning purposes
  • Effects on placement data due to bootcamps offered
  • Effect of tutoring on class grades

Data Science Presentation: Capstone Project

This is frankly not a very robust project data-wise. However, I am including it because it does showcase some visualization and presentation skills.
As a professor, I found it very interesting to cross-examine the Data Science Certificate program I completed through IBM. If I had had a hand in organizing the course, I would have pushed and pulled it in different ways.
I also thought some of the projects could have had much more potential if the course engaged in less handholding. It is entirely possible for a "student" to game the system in this certificate program, so I can understand why employers are wary of hiring candidates who don't show other means of proficiency.
The full presentation can be found here.

Musical analysis: re-tuning a midi file

This is an intricate Excel sheet that can take in a midi file and re-tune it to any tuning system in a long list (or enter you own), any key within that system and any mode within that key. The option also exists to translate variant setups to a common fundamental note so that the interval size differences will be the only thing you hear differently on playback.

(Link to the Excel file Coming soon)

Note: the import, export and play function in this sheet are supported by an Excel add-on called Tones-in-Tune which has unfortunately not been updated for current editions of Excel. I have future plans of writing something in Python to do the same thing by reading and writing a .midi file to .csv and back again.
tilt selective photograph of music notes
tilt selective photograph of music notes

Real Estate vs the Stock Market, A longview

This is a Mocrosoft Excel spreadsheet template for comparing home ownership with renting and investing equity instead. It can also be used to compare a rental investment property with a market investment. The model begins from the assumption that you own a home already and are curious to predict its appreciation over time as compared with market assumptions.
You can enter hypothetical or actual data at the monthly scale. Options include: extra payments, insurance and property tax rates, homeowner’s exemption amount, sales market rates , repair and improvement costs, tax and realtor fee rates upon sale, stock market rates, and rental rates.
Auto-calculated fields also run at the monthly scale and include: P&I, escrow, interest savings from extra payments, basis calculation for taxes, homeowners exemption adjustments, effective market rate if you were to view your house like an investment and sell.
This is a Python/Excel/VBA workbook which also processes financial data from savings, credit cards, and business accounts, insert metatags to sort into categories and subcategories, options for flagging outlier expenses and exclusion of particular values. Includes table look-ups.

(Link to the Excel file Coming soon)

black and silver laptop computer
black and silver laptop computer
white and red wooden house beside grey framed magnifying glass
white and red wooden house beside grey framed magnifying glass

Changing Real Estate investments given current higher market rates

Similar to the project above, I started this project to explore the effects of leverage in a real estate investment at the cheaper rates of a few years back with cash investments due to the current higher rates. Considerations I want to model include:
  • The effect of losing money to closing costs and capital gains now vs. later
  • The growth potential of a small cash investment compared to the leveraged one
  • Monthly earning potential given differences in rent rates for each option and mortgage payment
  • Leaving real estate altogether in favor of market investments
  • Is it a question of monthly cash flow vs. long term gain or can one have both?
As this project is currently based off of my own portfolio, I am unwilling to upload a copy until it's finished and fictionalized with mock data. Please contact me if you are interested in commisioning something like this.

Got a Data Analysis need?

Let’s get in touch.