Integrating Textual and Visual Information Into a Powerful Visual Search Engine
GSI Technology recently hosted a panel discussion on visual search at ODSC West 2018. The panel featured presentations from Clarifai, eBay, Google, Walmart Labs/Jet.com, and Wayfair. This blog post summarizes Walmart Labs/Jet.com’s panel presentation from the conference. Their presentation showed how they used Elasticsearch, a popular text search engine, to build a... Read more
7 Tips for Visual Search at Scale
Visual search is a rapidly emerging trend that is ideal for retail segments, such as fashion and home design, because they are largely driven by visual content, and style is often difficult to describe using text search alone. It is a topic of interest to data scientists, as evidenced... Read more
5 Ways To Make The Most Out Of An Expo Hall Experience
The expo hall is an exciting part of any conference. There’s so much going on, the freebies, the new tech, the possibility of finding your next big thing. I know you’re tempted to wing it, but you’d be making a mistake going in without a clear plan of action.... Read more
5 ODSC Talks to Teach You Machine Learning Today
The internet provides an abundance of content to teach you how to implement machine learning algorithms. Are you overwhelmed and unsure where to begin? These videos of top-rated Open Data Science Conference talks are a great introduction to the topic and offer a great starting point to launch into... Read more
Watch: Applied Finance – The Third Culture with Steve Lawrence
What can financial analysts learn from computer scientists about data science? And can computer scientists change their approach to appeal to finance professionals? Data scientists typically argue about the relative merits of the statistical and algorithmic approaches to data mining (Leo Breiman – The Two Cultures). Anyone who has... Read more
The Latest Advances in Classification With Too Many Labels
At ODSC London 2018, Dr. Michael Swarbrick Jones, Ph.D. gave a technical lecture on the latest in large-scale multilabel classification and how practitioners should be managing their hyperparameters and data to get the most out of their models, focusing specifically on problems where there are thousands or tens of... Read more
How to Fix Data Leakage – Your Model’s Greatest Enemy
At ODSC London 2018, Yuriy Guts of DataRobot gave a talk on data leakage, including potential sources of the problem and how it can be remedied. Data leakage – also sometimes referred to as data snooping – is a phenomenon in machine learning that occurs when a model is... Read more
Going to the Bank: Using Deep Learning For Banking and the Financial Industry
At ODSC London 2018, Pavel Shkadzko explained to the audience how Gini GmbH, where he works as a semantics engineer, uses deep learning to automate information extraction from financial documents, such as invoices. By applying deep learning to tasks historically handled by optical character recognition and clever regular expression... Read more
Digital Transformation and Agile Decision-Making in Commerce
Dr. Kanishka Bhattacharya spoke at ODSC London 2018 on how data science is changing commerce and enabling large companies to become more “agile” in their decision process. Dr. Bhattacharya, who works as a senior director at Publicis.Sapient, explained that large corporations with ‘traditional’ business models are failing to meet... Read more
Why Consumers Should Trust Companies with Their Data
Hugo Pinto is an asthmatic. He’s aware of the environmental triggers that can induce an asthma attack, but he wasn’t satisfied with the option that faces most asthmatics: wait until an attack happens, and treat the symptoms once it does. At a hackathon, Pinto teamed up with other developers... Read more