Live Webinar - Optimize LLM performance through Human-AI Collaboration

Improved Search Engine Listings with Local Content Evaluation

The company partnered with our crowd to improve the quality of its local listings after working on multiple successful projects with the firm.
March 27, 2020
Share

The Company

A leading multilingual search engine and mobile app provider tasked us to improve the quality of its local business listings, including addresses, phone numbers, hours of operation, maps, and directions.

The Challenge

A leading multilingual search engine and mobile app provider had users across the world relying on its data to find local business information, including addresses, phone numbers, hours of operation, maps, and directions. The search engine relied on algorithms supported by an in-house team to serve the most relevant and accurate results to its users. The firm’s existing process for adding and updating local business information was unable to keep up with the increased presence of businesses on the internet. Failure to keep local listings up-to-date could result in users losing confidence in the search engine’s data and turning to its competition for future queries. Verifying that local listings were being returned accurately was of critical importance to retaining the search engine’s local site traffic.

The Solution

The company partnered with us to improve the quality of its local listings after working on multiple successful projects with the firm. The provider highly valued our many years of industry experience, its worldwide crowd, and its strong project management expertise.

Based on the company’s specific needs, we developed an approach to ensure that business listings were as accurate and relevant as possible for its customers all over the world. In-market evaluators were hired and qualified to review, verify, clean, and label all types of data. The project started with ten evaluators in one market working on a single task, and within two years it had ramped up to 440 evaluators across 31 markets, working on eight different tasks. Our in-market crowd researched, called, or visited local businesses to verify and correct the accuracy of the listings—at first just name, address, and phone number were reviewed, but later other attributes such as hours of operation, geolocation, website, and business category were added. Businesses that did not have a verifiable web presence required a phone call or in-person visit to verify, so having evaluators located in-market was crucial to the project’s success.

The Result

Through its partnership with us over the past two years, the provider has greatly improved its local search listings. During this time, we have verified and corrected data for more than 750,000 of the client’s business listings, improving the overall user experience. Our Local Search Content Evaluation team has exceeded expectations by quickly evaluating search engine queries, business listings, duplicate results, and business classifications.

The use of our global, in-market crowd greatly reduced the potential data noise generated from time-zone differences, language barriers, and cultural and geographical considerations. Our proprietary quality and performance measurement systems enabled the delivery of the highest quality data back to its client, quickly and clearly. We have consistently provided data to meet client needs to identify root causes, adjust algorithms, and confidently deliver local listings to its users.