Beatriz Simoes

At AmbevTech (AB InBev), I had the opportunity to work with the most varied types of resources, which gave me a highly qualified experience such as: developing and deploying machine learning models, A/B tests, clearing data, high experience in platforms like databricks, git, azure AI services and more.

I have worked in a project with Data Collection and Data Analysis. Most of data describe information about financial products and they are extracted from their respectively websites. The data is collected using webscrapers like the BeautifulSoup and Requests libraries. They are later used for training Machine Learning classification models with Keras, Scikit-learn and Tensorflow. The project has been developed mostly in Python with some usages in R.

We propose a new generalization of the three-parameter Weibull distribution, a new invertible bimodal Weibull model (NIBW), which can be bimodal and its cumulative distribution function and quantile function have a simple and closed form, which makes it very interesting in simulation procedures and for the calculation of risk measures in the applied areas.

Due to the lack of discrete probabilistic models in the area, proposing a little-studied distribution that has a good fit to censored data is of great interest. The data set used refers to the Special Zone of Social Interest (ZEIS) policy and the proposed model verifies the influence of each covariate on the time for Brazilian municipalities to adhere to the policy. Finally, residual analysis is used to validate the model. The analyzes were carried out using the R software.