Industrial companies consider the process, an important area and opportunity to obtain greater profits based on the study of systematised information.

Data science is the study of the algorithms and processes that have to be carried out to extract knowledge from data. Its influence covers different areas of knowledge such as: agriculture, livestock, medicine, social studies, business sector, telecommunications, among others.

It is in this context that the research of Dr. Amilkar Puris, research professor at UTEQ, one of the winners of the seventh Focicyt call for proposals, arises. The objective of the research project focused on applying Data Science techniques in complex study scenarios.

Two important areas of knowledge were addressed:

1- Computational Chemistry: Model to classify the inhibitory activity of two anti-diabetic enzymes (?-amylase and ?-glucosidase) that regulate blood sugar.

2- Education: Exercise recommendation system to strengthen the informal learning of programming in first module students of careers with a computer science profile.

What were the results? For the first problem, the original problem was transformed from Regression to Classification and then a Decision Tree model was obtained with an accuracy of over 80%, which allowed Chemical Engineers to interpret the associations and understand the specific situations that were discovered. This result was published in the journal JCR, Chemical Biology & Drug Design, under the title "Beyond model interpretability using LDA and decision trees for ? amylase and ? glucosidase inhibitor classification studies", https://doi.org/10.1111/cbdd.13518

On the other hand, an exercise recommendation system was built taking into account the relationships between students with similar perceptions in the learning process. This system was part of a platform called "Caramba" (Scratch + Recommendation System) that in its testing stage proved to have a significant impact on the development of basic programming skills, improving students' performance and motivation. This result was published in the JCR journal, IEEE Transactions on Learning Technologies, under the title "Recommender Systems and Scratch: An integrated approach for enhancing computer programming learning", DOI: 10.1109/TLT.2019.2901457.