Advanced Training

Machine Learning and Data Analytics

From descriptive analysis to predictive analysis

 

Objectives

At the end of the course students will be able to use import, exploratory analysis and data transformation techniques, as well as to train and develop predictive analysis models to support management decision making.

We will be using R language and R Studio editor to solve case studies.

The public target for this course is professionals who are seeking to evolve from descriptive analysis to predictive analysis using automatic learning algorithms and data extraction techniques.

The students will have a training certificate at the end of the course.

Who should attend

Managers, analysts, controllers, CFOs, consultants, accountants or early career professionals looking to specialize in these areas

Programme Outline

Day 1

Introduction

  • Fit the Artificial Intelligence (AI) in companies and businesses
  • Data abstraction, generalization and knowledge extraction
  • CRIPS-DM model
  • Useful resources available online

Introduction to R Language

  • R and R Studio installation
  • Data types
  • Import data from files, databases and other online sources
  • Vectors, factors, lists and data frames
  • Tidyverse, lubridate, care and ggplot2

Exploratory data analysis

  • Central trend measures and dispersion measures
  • Visual data mining: understanding the grammar of the graphs
  • Boxplots, histograms, scatterplots and correlation matrices

Preprocessing data

  • Integration, balancing, transforming and cleaning data
  • Sampling techniques
  • How to deal with the “curse of dimensionality” with Principal Component Analysis and factor analysis
Day 2

Predictive models

  • Understand the functioning of different types of supervised and unsupervised models
  • Classification models and regression models
  • How to predict demand with simple and multiple linear regression
  • Classification models with the K-nearest neighbours algorithm
  • Decision trees and regression trees
  • How to evaluate the effectiveness of predictive models

Clustering

  • Identify market segments with k-means and Partinioning Around Medoids (PAM) algorithms
  • Evaluation and optimization of clustering algorithms

Descriptive models

  • Discover behavior patterns from data
  • Frequent item sets
  • Apply the Apriori algorithm to transactional data
  • Which products are best sold together?
  • Evaluation of descriptive models

Studie cases

Resources

Students must bring their computer, with Excel and R Studio installed

Requirements

There are no requirements  for this course. We will accept trainees  from diferent areas, even if they do not have knowledge of Power BI or Excel.

Locations and Dates

Oporto

  • Date: March 19th and 20th, from 09h00 to 18h00
  • Location: Rua Engenheiro Ferreira Dias, 161 – Porto

Lisbon

  • Date: February 18th and 19th, from 09h00 to 18h00
  • Location: Lisbon

Duration

16 hours

Trainer

Nuno Nogueira, manager with 20 years of international experience in finance and author of the book “Power BI for management and finance”, form FCA Editor, is graduated in Business Administration from the Catholic University, Executive MBA from Oporto Business School and Post-Graduate in Finance and Taxes from University of Oporto, will be the trainer in this course and will help you to make the most of the potential of Power BI technology.