How does Riminder structure your data ?
Structuring a resume requires two key technologies : semantic segmentation (extracting personal information, experiences, education, skills, interests, etc.) and entities recognition (names, email, phone, occupations, degrees, companies, schools, etc.). Our algorithms leverage both Deep Computer Vision and Deep NLP methods to get the best precision and performance. And since we also wanted to do that at scale, we optimized our models so that they could run in milliseconds!
How does Riminder’s talent recognition technology work
Our computer models are trained on the list of all possible job titles so they can be applied to any profile/CV database. Using machine learning, a process which enables a computer to learn from data and draw its own conclusions, by leveraging both external career paths and internal knowledge about your company's employees, our models are able to automatically identify the best candidates, for any job position. These models are also getting smarter with every interaction and feedback.
How does Riminder explain the evidence behind a specific decision ?
Deep Neural Network algorithms are often described as a black box. Basically, they show a trade off between interpretability and precision. Our technology leverage both Neural Network architectures with memory and with attention to exhibit certain reasoning capabilities required to understand the evidence behind the models’ conclusions. This gives us the ability to maintain an excellent accuracy level while improving the interpretability of the results.
Introducing Riminder AI for everyone
Riminder API allows HR Software companies to build AI-powered Talent Recognition Apps faster by bringing to them the power of our models. We made them easily accessible through a simple REST API. Now, everyone in the HR Industry can benefit from integrating Riminder.