The course is held by prof. Laura GRASSINI (6 ECTS) and prof. Francesca GIAMBONA (3 ECTS).
PART 1. Laura Grassini (3 ECTS). Statistical quality control.
PART 2. Francesca GIAMBONA (3 ECTS). Financial statement and distress analysis. Productivity and efficiency.
PART 3 (3 ECTS) laura Grassini
Data mining and machine learning.
Analysis of logfiles. Sentiment analysis.
Basic reference.
Biggeri L., Bini M., Coli A., Grassini L., Maltagliati M. (2012) Statistica per le decisioni aziendali. Ed. Pearson, Milano.
Learning Objectives
KNOWLEDGE. Significant measures and indicators for business: statistical quality control methods, benchmarking analysis, efficiency, productivity, evaluation of firm's performance through financial statement analysis (profitability, financial distress, etc.).
Multivariate analysis with unsupervisioned and supervisioned methods. Web surveys. Software for statistical analysis and data collection.
SKILLS. Ability for evaluating firm's performance: quality process capacity and contro, computation of efficiency, productivity, profitability measures for monitoring firm's performance and for benchmarking activities. Application of multivariate methods on new data sources like: Twitter data, logfiles, scanner data. Ability of understanding statistical packages outputs. Ability of planning and carrying out a web survey.
Oral exam for PART 1 and 2 (6 ECTS) 70%
PART 3 (3 ECTS; Oral exam + project ) 30%
Course program
The course aims at providing knowledge and skills for the collection and processing of data for the construction of significant measures and indicators for business.
Outline of the course.
Production Process: Quality Concept, Process Capacity Measurement and Online Monitoring Techniques (Variable Control Charts: x-bar chart, S-chart, S2-chart, Rchart, MR-chart and attributes). Not normality and control chart. Attribute control chart: p-chart, c-chart, uChart.
Efficiency and productivity analysis. Technical efficiency: parametric and non-parametric methods. Partial and total-factor productivity.
Business Performance Indicators from financial statement data. Financial ratios.
Data mining and machine learning. Supervised methods (classification trees and CART, k-NN, naive Bayes) and non-supervised (associative rules, clustering).
Special issues and topics: text-mining of Twitter data, analysis of logfiles