Villalón-Turrubiates, Iván E.Viveros-Wacher, AndrésTéllez-Salmón, Ximena2022-09-012022-09-012022-07Téllez-Salmón, X. (2022). Machine Learning and Data Science Techniques applied to Intel Historical SDL (Security Development Lifecycle). Project Execution Data to discover improvement insights. Trabajo de obtención de grado, Maestría en Sistemas Computacionales. Tlaquepaque, Jalisco: ITESO.https://hdl.handle.net/11117/8165Intel, as many other companies, wants to optimize their processes. Deliver products faster without compromising quality is one of the main objectives of the company. Security is one of their quality pillars. Ensuring that their products are secure is a priority. Because of that, one of our organization’s main goals is to reduce the time teams spend in security related activities. The main intention of this work is to use data science to improve the security development lifecycle (SDL) process. Optimizing SDL by using machine learning models to identify delays and unnecessary tasks became the specific objectives of this work. Two machine learning models are proposed as the result of this effort that are explained in full detail at the results section. This document contains 6 main sections. The first section which is the introduction, explains the reasons behind this work. The second section is the state of the art which explains how other companies have improved their processes by using data science and machine learning techniques. The third section is the theoretical framework; in this section all the concepts that were used on this work are explained in detail. Fourth section is the methodological development which explains the steps followed and techniques used to deliver results. Fifth section are results. In this section, the results of each phase are explained in detail, and finally what is the outcome of this work. Finally, the sixth section are conclusions, which discuss the impact of this work and the work ahead.enginfo:eu-repo/semantics/masterThesis