Marketplace Data Generation

Marketplace Data Generation

AKA Be The Dataset You Want To See In The World

Problem: We want to practice extracting insights from datasets resembling what we might encounter at a marketplace company like Doordash, Lyft, or Uber. The ideal public dataset doesn't exist.
Solution: Generate our own universe of marketplace company data. Duh.

View Notebook (1 of 3)  |  View Dashboard (2 of 3)

Data Science Machine Learning

Collaborative Filtering, Explained

AKA How Netflix Decides That Recommending Moana is a Universal Good

Where we learn about collaborative filtering, a technique for building the type of recommender systems used by Netflix, Amazon, and Spotify.

View Spreadsheet

Data Science Machine Learning

Personalized Images at Scale

AKA The Robots Are Here To Take Our Jobs Starting With Sales Development

SDRs put a lot of work into outbound messaging to capture the attention of prospects. What if they could... Not do that work?

View Notebook

Marketing Automation Python

Frictionless Demo for Base

How We Gave Everyone What They Wanted (Increasing Conversions 100%)

We want the people who want product demos to fill out forms. The people who want product demos don't want to fill out forms.

View Demo

Marketing User Experience JavaScript

90% Data Cleaning / 10% Insight

WTF is The City Doing? An Exploration of the 2017 San Francisco Budget

View Deck

Government Data Visualization

Browserbowl: Recommendations for Firefox in the Year of Our Lord 2010

View Deck  |  View SQL

Product Data Analytics

Machine Learning & Terrorism (I Promise I'm Not Training Robot Terrorists)

View Deck

Global Machine Learning

Gradient Descent, Explained

Where we explore gradient descent, the algorithm that helps neural networks find truth in the world. This one is interactive.

View Spreadsheet  |  View Gist

Data Science Deep Learning

Convolutions, Explained

Where I make some 90s pixel art in a spreadsheet and call it deep learning. Not really. But kinda. AKA how do computers learn to see?

View Spreadsheet

Data Science Deep Learning

Neural Network Layers, Explained

Where we briefly discuss famous datasets (ImageNet, MNIST), and dive into the different neural network layers (Lambda, ZeroPadding, Convolution, MaxPooling, Flatten, Dense) in the Keras library.

View Notebook

Data Science Deep Learning

Things are a bit of a mess here. You've basically caught me in the midst of moving a couple things around.

You can find my current obsession here at One Data Science a Day.

I guess I could tell you a little bit about myself.

I grew up in Kuala Lumpur and Singapore, went to college in Columbus and moved to Chicago right after.

I currently live in San Francisco.

I try to have something different to say about the subjects I write about, which might be why I don't publish all that often. I think good writing takes time, and sometimes you have to live through things to be able to write about them. But I also think good writing takes practice, which is why this space exists.

What else?

Current projects:

Previous projects:

  • 🕵️  Detective, Elephant Investigations
  • 📊  Growth-Hacker-in-Residence, MaGIC
  • 🌏  Digital Nomad/Vagabond, South East Asia

Future projects:

  • 💡  Put on pants both legs at a time
  • 🚀  Send Snapchats from Mars

You can reach me multiple ways, the fastest of which would be to send something to my Snapchat (actually don't do this it turns out I'm really bad at accepting friend requests from strangers). But you can also email me at, if you're into that kind of thing.