This is a guest post by Audrey Boguchwal of Samasource, Quid’s longtime business partner in our company data acquisition pipeline. It was originally published here to showcase how Samasource’s web research and data cleaning services help collect data for Quid to build our natural language processing-powered data platform. How does Quid create business intelligence? Here at Quid, we are working to ingest the world’s collective intelligence. Our goal? Help business decision makers quickly gain the insights they need to make more informed decisions. Quid’s product is a platform that searches, analyzes and visualizes data to deliver key insights. Customers bring questions such as, “What does the current landscape look like for financial technology?” For each question, Quid creates a custom visual interactive map from raw business data: documents and articles. The map illustrates the network of relationships between documents: the closer together the nodes, the more similarities exist between the data. With Quid, users can quickly find topic similarities, uncover hidden relationships, and draw insights that might otherwise take a researcher hundreds of hours. To create its visual maps, the Quid platform pulls information from three premium data sets: Companies, News and Blogs, and Patents (as well as custom uploaded […]
Read MoreOur First Engineering Game Day
Chaos Engineering ideas are gathering steam these days. In August we ran an engineering-wide Game Day here at Quid, where we simulated real-world service failures and had “on-call teams” exercise their incident response skills. It was great fun and good training for Quid engineers. This post covers the organizational side of Game Day, lessons learned, and some technical tricks that others can use in similar exercises.
Read MoreImproving search with Word2Vec and Wikipedia
Quid wants to show you the most relevant results when you perform a search. A part of the job of our search is to get the most signal from each term. Ben Bowles, a resident data scientist, describes an ongoing experiment for using related terms to help users get more relevancy: Sometimes users have a generic interest, like “artificial intelligence” or “Brexit.” Often the key to getting the best search results is knowing all the different ways to refer to these concepts, and knowing all related terms to the topic at hand. To help with this, we are now providing suggestions below the search bar as users start to type in a query. Read more on our experiment with Word2Vec and Wikipedia on quid.com. Interested in helping us solve awesome problems? If so, then head over to our careers page!
Read MoreManaging text data you haven’t seen and can’t control
There is a lot that you need to predict, and a lot that can go wrong, when working with text data you have little control over. In this post the Quid technology team explores the methodologies used when addressing these challenges. By: Vincenzo Ampolo, Ashkan Zadeh, Fabio Ciulla, Mark Longo, Ruggero Altair Tacchi This month, Quid launched Opus, a new capability in Quid that lets you visualize and analyze any text-based data. Many users have ways to analyze structured data, which is why everyone is so familiar with Excel. But things become more complicated when, in addition to categorical and numerical data, there is also text-based data in the mix. Almost every survey has fields in which people can type their comments, but those fields rarely are analyzed systematically for lack of good tools. Our goal is to make that analysis easy, fast, and insightful. To help users get insights from unstructured text data, we took a series of steps to guide them towards their goals. One simple example: the way you define the ‘type’ of some metadata (is it a list? a number? a comment?) will eventually determine how that datapoint is ultimately available in the interactive software […]
Read MoreUsing deep learning with small data
Quid maintains an incredibly diverse set of company descriptions. A priority for Quid is identifying company descriptions of poor quality and improving them before they even get into our index. Ben Bowles, a resident data scientist, wrote up a great article featured on our parent blog on our approach to separating the “good” from the “bad” with very little data to go on: We developed a strategic goal at Quid to use machine learning to identify marketing language that conveys very little information. In fact, we combined this goal with recent advances in deep learning and a bit of an experiment: to see whether deep learning really requires “big data,” or whether small data can suffice. Read more on our approach to deep learning with small data on quid.com. Interested in helping us solve awesome problems? If so, then head over to our careers page!
Read More