Specialized program in Data Science - Decisions based on data (Online)

Aim

To provide participants with an understanding of the strategic application of data science in business contexts, emphasizing the importance of identifying business needs, developing relevant use cases, and employing different types of analytics.

1. Business needs
2. Use Cases
3. Analytics: descriptive, diagnostic, predictive and prescriptive
4. Business Transformation
5. Data Science
6. Data Science Professionals
7. Roles and responsibilities of professionals in Data Science
8. Tools of a data analyst

Aim

To introduce participants to the concepts of programming with Python. Understanding syntax, data structures, flow control, Python operations, as well as different libraries necessary to model, analyze, and visualize information obtained from data.

Basic Data Analysis Tools

• Main tools of the Data Analyst
• Spreadsheets: Excel and Google Sheets
• Databases: SQL Fundamentals
• Data visualization tools

Fundamental concepts of Data Science

• Fundamental concepts of programming languages in Data Science
• Current SDIs for the development of Data Science
• Fundamentals of the R Programming Language and R Studio
• Python and Colab

Libraries in Python

• Matplotlib Library
• Pandas Bookstore
• Seaborn Bookstore
• Scikit-learn Library
• Other Bookstores

Data preparation

• Definition of variables
• Lists and structures
• Data management with Numpy and Pandas libraries

Data Modeling and Visualization I

• Model type selection (libraries)
• Libraries for different types of analysis: NumPy, Matplotlib, Seaborn, SciPy

Data Modeling and Visualization II

• Libraries for Machine Learning: Scikit-learn, Tensorflow
• Data analysis
• Visualizing data and statistical graphs with Matplotlib and Seaborn

Data Analysis Case Study

• Complete Data Analysis case study, from conception to data visualization

Aim

Develop a deep understanding of fundamental statistical concepts and their application in data science. This module is designed to teach participants how to prepare, analyze, and interpret data using statistical methods, with the goal of supporting effective business decision-making. It will focus on descriptive and inferential techniques, with practical examples using Python.

Descriptive statistics

• Introduction to Statistics: Population and Sample
• Types of variables and measurement scales
• Grouped data and frequency table

Data preparation

• Data transformation and discretization
• Data cleansing
• Outlier Identification

Descriptive analysis

• Measures of central tendency: Mean, Median, and Mode
• Measures of dispersion: Range, Quantiles, Variance and Standard Deviation
• Creation of histograms and box plots.
• When to use it? What questions does it answer?

Statistical inference

• Relationship between quantitative variables: correlation coefficient
• Relationship between qualitative variables: Chi-square test
• Hypothesis testing and its application in decision making.
• When to use it? What questions does it answer?

Aim

To train participants in the fundamental principles and techniques of regression, machine learning, and artificial intelligence, with a practical focus on their application in decision-making in business environments.

Participants will learn to select, implement, and evaluate models using Python, with a special emphasis on how these models can be defined and applied to achieve specific business objectives.

Simple and multiple linear regression

• Definition and assumptions of linear regression
• Interpretation of regression coefficients
• Evaluation of the model's goodness of fit

Nonlinear regression models

• Definition and examples of nonlinear regression models
• Methods for fitting nonlinear models
• Goodness of fit assessment in nonlinear models

Artificial Intelligence and Machine Learning

• Introduction
• Definitions
• Concepts
• Processes and Applications
• Types of Learning

Supervised Learning

• Logistic regression
  • Introduction and Definition
  • Model assumptions
  • Model formulation
  • Parameter estimation
  • Application

Validation of Supervised Learning models

• Confusion Matrix
• GINI
• KS
• ROC
• Sensitivity
• Specificity

Supervised Learning

• Classification Trees
• Random forest
• SVM (Support Vector Machines)
• Naïve Bayes
• Applications

Supervised Learning

• Neural Networks
  • The Neuron
  • Operation
  • Architecture
  • Perceptron
  • Activation Functions
  • Application

Unsupervised Learning

• K-means grouping
• Main Components
• Applications

Fundamentals of Deep Learning

• Multilayer Perceptron

Aim

This course aims to develop participants' skills in evaluating, selecting, implementing, and monitoring analytical models, prioritizing their applicability to real-world business problems. Participants will learn to balance model accuracy, complexity, and interpretability, enabling them to make data-driven decisions aligned with their organizations' strategic objectives.

Model estimation

• Selection of explanatory variables
• Regression model estimation
• Waste Analysis

Model validation

• Cross-validation and data partitioning
• Model evaluation metrics: R2, MAE, RMSE, etc.
• Interpretation of model evaluation metrics

Model selection

• Model selection methods: MSE, MAPE, AIC, BIC, etc.
• Model comparison and selection of the best model
• Interpretability vs. complexity of the model

Implementation of models

• Implementation of models
• Integration of models into business processes
• Practical considerations for the implementation of models

Model monitoring

• Monitoring the performance of models in production
• Detection and diagnosis of problems in models
• Updating and retraining production models

Global Application of the Best Model