IMFD Innovation collaborates with the Superintendence of Social Security in project using advanced NLP techniques
August, 2024. How to put the most advanced data science techniques at the service of people: this is the objective of the IMFD Innovation area, which in collaboration with the Superintendence of Social Security (SUSESO), is working on the project. "Natural Language Processing for Claims Entry Optimization".
SUSESO is the autonomous state agency in charge of overseeing compliance with social security regulations and guaranteeing respect for the rights of individuals, especially workers, pensioners and their families. The organization is working for the first time on solutions with data science and artificial intelligence, in this case with natural language processing (NLP) as part of its efforts to improve service and modernize its processes.
A project with citizen impact
The initiative is part of a total of 11 projects promoted by SUSESO and its main focus is to optimize the entry of claims from a citizen's perspective. This will not only streamline the process, but also facilitate a faster and more accurate response for those seeking solutions to their problems. solutions to their problems.
"This is making available something that sometimes seems so far away, such as artificial intelligence, in something concrete. Innovation is coming, which is to improve the user experience of our people who come to knock on our door to solve claims. We are very happy because the project has a clear citizen impact, with a high technological and development level", said Pamela Gana, SUSESO's Superintendent.
Looking for an innovative solution
The IMFD team behind this project is led by Hernán Sarmiento, IMFD Innovation Transfer Engineer, Francisca Cona and Camila Henríquez as data scientists, and Jocelyn Dunstan, an academic from the UC Department of Computer Science in shared position with the UC Institute of Computational Mathematical Engineering, AC3E and IMFD researcher, as consultant.
The project is divided into three key stages: Exploratory data analysisin which claims will be reviewed to identify patterns. Linguistic characterization of the storieswhere they will use NLP tools. And finally they will arrive at model training and validationwhich involves training artificial intelligence models to automate the classification of claims.
"In a first stage we explored data relating to income forms (not including personal information) and narratives in textual format. In order to understand the scope and complexity of these sources, we focused on identifying patterns and anomalies that may exist in the data. Fortunately, this process has been very agile and expeditious thanks to the efforts of SUSESO's technology area", mentions IMFD Innovation Engineer Hernán Sarmiento.
In addition, the project leader comments that "we are currently developing the characterization of the stories through NLP techniques. This will help us to have a general overview of how to computationally represent each story, an approach that will be useful for the final classification phase of the project".
Jocelyn Dunstan emphasized the importance of the collaboration with the Superintendency of Social Security, which already allows technology transfer in areas where it is most needed, such as the public system.
For IMFD, this project represents an opportunity toapply data science research to the solution of problems that impact society.
