Hi! I’m Patti Shih.
I’m currently an independent data scientist and a technical consultant in the transportation industry. In my former life in academia, I studied computational cognitive neuroscience.
Four Pillars of Patti
A scrappy data scientist with a diverse and versatile skill set
Data Analytics
/ Machine Learning
9+ years of experience in applied statistics and machine learning, but my specialties are in time series and user-behavior data.
Programming
I currently use Python, SQL, bash, and sometimes JavaScript.
Communication
Whether through words or pictures, I’ve spent years crafting my skills in communicating to diverse audiences. Check out my writings in my Blog!
Doing Good
While I intrinsically enjoy solving problems, I am driven most when my work has positive impact.
Proud alumna of…
University of California
San Diego
BSc in Bioinformatics and Psychology
San Diego State University
MA in Psychology
Brown University
MSc in Computational Cognitive Neuroscience
Data Science Portfolio
Under construction—please stay tuned for updates as I put the finishing touches on the work that I’d like to share!
-
![[Dashboard] Fitbit Dashboard with Google Sheets—An Exercise in Presenting Data Purposefully](https://pattishih.com/wp-content/uploads/2023/05/Fitbit-Dashboard-Activity-at-a-Glance.png)
[Dashboard] Fitbit Dashboard with Google Sheets—An Exercise in Presenting Data Purposefully
The dashboard presents visualizations and analysis of Fitbit fitness and health tracking data collected from my Fitbit Charge 4 from November 1, 2021 to March 3, 2022. While I started creating it because I wanted to know whether there were any relationships between fitness and health metrics, it later became an exercise in creating a… Read more…
-
![[Project] A nostalgic look back at HQ Trivia and my python automation experiment for getting rich](https://pattishih.com/wp-content/uploads/2023/04/hq-money-winnings.png)
[Project] A nostalgic look back at HQ Trivia and my python automation experiment for getting rich
Does anyone remember the fall of 2017? That’s when HQ Trivia took the world by storm. This live mobile trivia game initially featured 10 questions and ran only twice a day, attracting millions of eager players vying for cash prizes. My friends and I were no exception, gathering together in a Discord channel every day… Read more…
-
![[Case Study] Game analytics and insights from player segmentation analysis](https://pattishih.com/wp-content/uploads/2023/03/stickiness_metrics.png)
[Case Study] Game analytics and insights from player segmentation analysis
A niche free-to-play online survival game was facing the problem of diminishing annual revenue over time and was seeking new avenues for monetization and retention. Leveraging a dataset of in-game user activities, load-outs, and states, I employed clustering algorithms to segment players into distinct groups based on their behavior, preferences, and engagement. The analysis… Read… Read more…
-
![[Case Study] Optimizing the application screening process with NLP and machine learning](https://pattishih.com/wp-content/uploads/2023/03/nlp_data_project_wordcloud-1.png)
[Case Study] Optimizing the application screening process with NLP and machine learning
DonorChoose.org is a non-profit crowdfund platform for teachers to request resources for their classrooms. Founded in 2000 by a public school teacher and largely operated by volunteers, the website faced a scaling issue as the number of proposals grew exponentially every year. The solution was to use an algorithm to pre-screen applications and provide a… Read more…
-
![[Project] Emergent abstract representations in a recurrent neural network](https://pattishih.com/wp-content/uploads/2023/04/emergent_simple_recurrent_network.png)
[Project] Emergent abstract representations in a recurrent neural network
Deep learning is powerful but often a black box. To understand predictions, we need insight into what our models have learned. In this project, I examined the patterns of distributed activity in a simple Recurrent Neural Network (RNN) with a context memory layer. To simulate a toy Natural Language Processing (NLP) task, I trained my… Read more…
-
![[Current Project] Trade volume forecasting with deep learning](https://pattishih.com/wp-content/uploads/2023/03/stock_trade_data.png)
[Current Project] Trade volume forecasting with deep learning
Modeling changes in intraday trading volume is a key component in algorithmic trading strategies. Deep learning can be a useful tool for discovering new edges for investors, but for several reasons the use of recurrent neural network models in financial data have produced mixed results. In this on-going project, I explore the application of deep… Read more…
Anything here pique your interest?
I’d love to hear from you!
#CraftyDataViz Winner! 🎉
Winner of the “Most Beautiful” category of Becoming a Data Scientist’s first-ever #CraftyDataViz contest!
I recreated Circos diagrams using needle and thread. Circos plots are useful for visualizing relationships in a circular format. (Original report here)
A visualization of normal brain connectivity
And the hyperconnected brain on Psilocybin (magic mushroomS 🍄)
