Certified Data Scientist with a strong foundation in industrial engineering and a proven ability to leverage complex data sets to drive business impact. Adept at translating business challenges into data-driven solutions through advanced statistical modeling, machine learning, and data mining techniques. Possessing a solid understanding of data pipelines and a passion for exploring emerging technologies, I am committed to delivering actionable insights that inform strategic decision-making.
This predictive model can enable emergency services to prioritise and allocate resources more efficiently. Authorities can make informed decisions to divert traffic and avoid additional congestion. This is crucial to minimise the impact on the road network and reduce the risk of secondary accidents. The model was built in Python using libraries such as Matplotlib and Seaborn for visualisation, Scikit Learn, TensorFlow and Keras for training the model and finally, the deployment was done through Streamlit and Render.
Spearheaded the reduction of inventory fluctuation losses from 3.0% to 1.5%, significantly improving company assets. This goal was achieved by the identification of the categories that presented the greatest reduction factor; the analysis of the data aimed at increasing the cyclical counts of the merchandise, together with the technical review of the physical protection systems and the training of collaborators to deal with external and internal theft.
Managed a project that integrated CCTV and SAP systems to track orders throughout the value chain, from creation to dispatch. The implemented technology allowed for real-time tracking of orders, significantly improving the efficiency of the dispatch process.
Implemented satellite tracking technology and developed communication protocols with state security forces, improving real-time response to theft incidents. Use data from SAP to determine the areas of greatest risk for the operation, supported by a new design of the safe deposit boxes used for cash collection.