Project Overview
Germany-based construction technology company
Construction
Business Needs
A German technology company needed to enhance its in-house construction leads data platform to disseminate exhaustive and well-researched construction projects data across the USA and Europe. The company had a huge clientele that included small to Fortune 500 companies operating in the real estate, construction, and building materials manufacturing space. The company captured upcoming or existing construction projects data in real-time from multi-lingual and multi-format online publications.
The real-time data captured related to upcoming and existing construction projects that were parsed using automated crawlers. The data was auto-classified into relevant segments using intelligent AI algorithms. The segments included property type, project start/end date, site location, size, cost, and construction phases. The company partnered with Hitech BPO to help verify and validate the auto-classified text to ensure accuracy, append missing information, and manually annotate the 20% of data that couldn’t be auto classified.
The Challenges
- Comprehending and extracting relevant information from construction articles.
- Tagging or labeling the information based on categories like project size, phase, location, owner, architects, start date and end date, etc.
- Handling large volumes of articles with a 24-hour timeline without compromising on quality.
- Training the skilled workforce to comprehend data and validate auto-classified information.
Solutions and Results
Want to enhance the performance of AI models?
Speak to us today- The team did an in-depth project assessment to understand the client’s business needs and accordingly defined KPIs, SOPs, and other metrics.
- Domain and functional training were imparted by the client to text annotators and quality check specialists.
- The client provided credentials to access the auto-classified input data from the client portal.
- The auto-classified data was manually verified and validated to ensure the accuracy of the data.
- The data was further appended with missing information wherever required to improve future tool performance.
- Manually verified 20% of the articles which were complex and couldn’t be auto-classified.
- Each batch of articles was put through a 2-step vigorous quality check process to ensure labeling accuracy.
- More than 10,000 construction-related articles were classified and labeled by Hitech BPO’s specialist team.
- The verified and validated data improved the accuracy of the AI algorithms and ensured better and more relevant search results on construction project data.
Business Impact
50% cost reduction on the project
Enhanced AI model performance
Superior customer experience
