SmartDataCollective

  • Big Data is Merging Ecommerce and Brick-and-Mortar Retail in Exciting Ways
    I have been monitoring trends in the digital marketing sphere since the late 1990s. I can still remember the early predictions of traditional retail in the age of e-commerce. Many experts speculated that traditional retail stores would be driven out…
    - 4 days ago 23 May 18, 11:55pm -
  • Will 6G Force Cell Phone Providers to Redesign Their Data Servers?
    A few months ago, we highlighted the changes that 5G networks will soon be creating for mobile users across the world. Although no provider has actually launched a 5G network yet, the wireless industry developed the first official standard for the ne…
    - 4 days ago 23 May 18, 6:56pm -
  • Data-Driven eCommerce Case Study: Cohorts and Segmentation
    E-commerce is a rapidly evolving field. It is growing at a remarkable pace, largely due to the evolution of big data. Segmentation is one of the biggest advantages that it offers. At Metrilo, we analyzed, tens of thousands of ecommerce platforms from…
    - 4 days ago 23 May 18, 6:19pm -
  • Is Big Data Causing Insurance Actuaries to Move Away from Using Credit Scores?
    Insurance companies have literally spent decades fine-tuning their actuarial models. In the 1990s, they began using credit scores to assess the risks of customers and set premiums accordingly. Laws permitting credit score use with insurance companies…
    - 6 days ago 22 May 18, 7:30am -
  • How Data Security Remains More Than Just About IT Safeguards
    While the internet has transformed the business world for the better, it has also created a host of new issues for organizations to consider. Having an online presence has become a fundamental for many companies, but even establishing a website bring…
    - 6 days ago 21 May 18, 9:55pm -

AirBnB - Nerds

  • Categorizing Listing Photos at Airbnb
    Large-scale deep learning models are changing the way we think about images of homes on our platform.Authors: Shijing Yao, Qiang Zhu, Phillippe SiclaitWalking into our new office in San Francisco, meeting rooms evoke the variety of our listing photos…
    - 2 days ago 25 May 18, 7:16pm -
  • Growing Our Host Community with Online Marketing
    Which ads should we buy? How much should we pay for each ad? How should we measure the performance of each ad? We built a marketing system to help answer these questions.By Tao Cui, Ye Wang and Bassel NamihBelonging is at the core of Airbnb’s miss…
    - 5 days ago 23 May 18, 4:23am -
  • Building Services at Airbnb, Part 2
    The second in a series on scaling service development, this article looks at some of the key tooling that supports the new Services Oriented Architecture at Airbnb.By Liang Guo and Frank LinVittoria is treating his guests to a tour of the Limoncell…
    - 13 days ago 15 May 18, 3:01pm -
  • Listing Embeddings in Search Ranking
    Listing Embeddings for Similar Listing Recommendations and Real-time Personalization in Search RankingBy Mihajlo Grbovic, Haibin Cheng, Qing Zhang, Lynn Yang, Phillippe Siclait and Matt JonesAirbnb’s marketplace contains millions of diverse listi…
    - 23 days ago 4 May 18, 11:21pm -
  • The Smart Instant Book Filter
    Exploring a feature designed to help guests book with confidenceBy Yi Hou, Li Fan & Tao CuiPeople like it when things are fast. We want our deliveries within an hour, our downloads within a minute, and our news in an instant. That is why we need to…
    - 25 days ago 3 May 18, 5:51am -

Data Center Knowledge

The Unofficial Google Data Science Blog

  • Compliance bias in mobile experiments
    by DANIEL PERCIVALRandomized experiments are invaluable in making product decisions, including on mobile apps. But what if users don't immediately uptake the new experimental version? What if their uptake rate is not uniform? We'd like to be able to…
    - 67 days ago 22 Mar 18, 4:32pm -
  • Designing A/B tests in a collaboration network
    by SANGHO YOONIn this article, we discuss an approach to the design of experiments in a network. In particular, we describe a method to prevent potential contamination (or inconsistent treatment exposure) of samples due to network effects. We present…
    - 17 Jan 18, 2:04am -
  • Unintentional data
    by ERIC HOLLINGSWORTHA large part of the data we data scientists are asked to analyze was not collected with any specific analysis in mind, or perhaps any particular purpose at all. This post describes the analytical issues which arise in such a sett…
    - 13 Oct 17, 1:26am -
  • Fitting Bayesian structural time series with the bsts R package
    by STEVEN L. SCOTTTime series data are everywhere, but time series modeling is a fairly specialized area within statistics and data science. This post describes the bsts software package, which makes it easy to fit some fairly sophisticated time ser…
    - 11 Jul 17, 8:55pm -
  • Our quest for robust time series forecasting at scale
    by ERIC TASSONE, FARZAN ROHANIWe were part of a team of data scientists in Search Infrastructure at Google that took on the task of developing robust and automatic large-scale time series forecasting for our organization. In this post, we recount how…
    - 18 Apr 17, 12:02am -

IBM BigData and Analytics Hub

  • Making Data Simple: A look into Hybrid Data Management
    On this episode of Making Data Simple, we change gears as our guest Daniel (Danny) Hernandez, VP Analytics Offering Management, interviews host, Albert V Martin, VP of Hybrid Platform Development and Client Success. Learn how to create a long-lasting…
    - 3 days ago 24 May 18, 9:09pm -
  • The path to data veracity
    As the information age matures, data has become the most powerful resource enterprises have at their disposal. Learn how to leverage a trusted analytics foundation to achieve all your insight-driven goals.
    - 4 days ago 24 May 18, 11:28am -
  • Expert advice on data science: the rules of the game
    What happens when you gather experts in a room, give them a few questions to get them started, then let them go? You get an informative, spirited discussion like this one.
    - 5 days ago 23 May 18, 1:42pm -
  • Cognitive Data Governance
    A look into how machine learning and deep learning techniques can impact the way companies implement metadata discovery and business term assignments using the IBM Unified Governance & Integration platform.
    - 5 days ago 22 May 18, 5:57pm -
  • 5 fundamental questions for your data journey
    To accelerate its journey to AI, a data-driven organization needs a trusted data foundation that empowers information stakeholders. Stakeholders need the ability to discover, understand, integrate, analyze, govern and self-serve structured and unstru…
    - 6 days ago 22 May 18, 2:30pm -

Predictive Analytics