Data Science Weekly Newsletter - Issue 181

Issue #181

May 11 2017

Editor Picks
 
  • Scaling Airbnb’s Experimentation Platform
    At Airbnb, we are constantly iterating on the user experience and product features. This can include changes to the look and feel of the website or native apps, optimizations for our smart pricing and search ranking algorithms, or even targeting the right content and timing for our email campaigns. For the majority of this work, we leverage our internal A/B Testing platform, the Experimentation Reporting Framework (ERF), to validate our hypotheses and quantify the impact of our work...
 
 

A Message from this week's Sponsor:

 

 
 

Data Science Articles & Videos

 
  • Magic AI: These are the optical illusions that trick, fool, and flmmox ciomputers
    To a human, a fooling image might look like a random tie-dye pattern or a burst of TV static, but show it to an AI image classifier and it’ll say with confidence: “Yep, that’s a gibbon,” or “My, what a shiny red motorbike.” Just as with the facial recognition system that was fooled by the psychedelic glasses, the classifier picks up visual features of the image that are so distorted a human would never recognize them...
  • Facebook posts its fast and accurate ConvNet models for machine translation on GitHub
    In its latest paper, the Facebook AI Research (FAIR) team dropped some impressive results for its implementation of a modified convolutional neural network for machine translation. Facebook says it has achieved a small bump in accuracy at nine times the speed of traditional recurrent network models. And to complement its research, the company is releasing its pre-trained models on GitHub, along with all the tools needed to replicate the results on your own...
  • The Housing Value of Every County in the U.S.
    After the last post, which looked at housing values across New York City, I thought it would be interesting to take a more granular look at housing values across the U.S. To create the map below, I took the total residential property value for every county in the U.S. (the contiguous 48 states), and substituted those ves for each county’s land area...
  • Flight Paths Edge Bundling
    Visualizes flights between airports in the continental United States using edge bundling. The code can be easily modified to either show the top 50 airports by degree or the highest degree airport in each state. This example combines our map and graph visualizations together in a single visualization. It demonstrates map projections, topojson, force-directed layouts, and edge bundling....
  • Self-Study Plan For Moving From A Junior Data Scientist To A Senior Data Scientist
    You are familiar with the basics of data science and now you want to level up. You're familiar with applying off-the-shelf ML algorithms and have gotten your feet wet with data wrangling and messy datasets. Now you want to go beyond where you are now and improve your data science skills. Unfortunately most guides, FAQ, and articles you've encountered are ways to dive into data science not on how to go beyond the basics...
 
 

Jobs

 
  • Data Scientist/Statistical Modeler - Gain Theory - NYC

    Gain Theory is a global marketing foresight consultancy that brings together data, analytics, technology solutions and consumer-insight capabilities to help marketing and insight professionals make smarter, faster, predictive business decisions. In this role you will work within a team dedicated to delivering cutting edge capabilities to our clients. In particular, we are looking for someone to enhance our existing attribution models, and sales prediction models. A variety of technologies are in-play to include Amazon Web Services, Hadoop, Vertica, Python, and R. If you are looking for an opportunity to contribute to a growing company and work within a group of bright people driven to help our clients, read on...
 
 

Training & Resources

 
  • Intuitive Classification using KNN and Python
    K-nearest neighbors, or KNN, is a supervised learning algorithm for either classification or regression. It's super intuitive and has been applied to many types of problems. It's great for many applications, with personalization tasks being among the most common. To make a personalized offer to one customer, you might employ KNN to find similar customers and base your offer on their purchase behaviors. KNN has also been applied to medical diagnosis and credit scoring. This is a post about the K-nearest neighbors algorithm and Python...
  • pytorch-playground
    Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)...
 
 

Books

 

  • Smart Cities: Big Data, Civic Hackers, and the Quest for a New Utopia

    "Critical book for anyone interested in the way technology is shaping our cities. Great collection of many historical and current endeavors, and a strong perspective on the different approaches to solving urban issues with technology."...


    For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page.
 
 
P.S. Looking to hire a Data Scientist? Find an awesome one among our readers! Email us for details on how to post your job :) - All the best, Hannah & Sebastian
 
Sign up to receive the Data Science Weekly Newsletter every Thursday

Easy to unsubscribe. No spam — we keep your email safe and do not share it.