Intelligent Data Analysis Applications in Business

You are here

Home » Studies » Academic Management » Extinct Curriculums » Master in Artificial Intelligence - 2012
Credits
3
Department
UB
Types
Compulsory
Requirements
This subject has not requirements
The objective of this course is three fold, first to provide the student with a knowledge about recommender systems. Then to present different succesful applications in the field of recommender systems, and finally different presentations of companies that use these technologies.
Mail: ,

Teachers

Person in charge

  • Salvador Torra ( )

Others

  • Santiago Seguí Mesquida ( )

Weekly hours

Theory
10
Problems
11
Laboratory
0
Guided learning
6
Autonomous learning
48

Competences

Generic Technical Competences

Generic

  • CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to Artificial Intelligence.

Technical Competences of each Specialization

Academic

  • CEA7 - Capability to understand the problems, and the solutions to problems in the professional practice of Artificial Intelligence application in business and industry environment.

Professional

  • CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.
  • CEP5 - Capability to design new tools and new techniques of Artificial Intelligence in professional practice.

Transversal Competences

Solvent use of the information resources

  • CT4 - Capacity for managing the acquisition, the structuring, analysis and visualization of data and information in the field of specialisation, and for critically assessing the results of this management.

Analisis y sintesis

  • CT7 - Capability to analyze and solve complex technical problems.

Objectives

  1. Understand the general behaviour of the recommender systems
    Related competences: CT7,
  2. Understand the specific properties of the Multilayer perceptron and Radial Basis Functions when applied to financial data
    Related competences: CT4,
  3. Understanding how recommender systems work to address the big amout of existing data.
    Related competences: CEA7, CEP3,
  4. Understanding the potential applications of recommender systems in the industry
    Related competences: CG3, CEP3,
  5. Understanding the potential applications of AI in the business environment
    Related competences: CEP5,

Contents

  1. Recommender Systems for industrial applications.
    We will give an overview of different kinds of recommenders systems. From non-personalized to personalized recommeders.
  2. Collaborative Filtering
    We will explain how statistics that characterize the financial data affect the learning algorithms that are allow to infer the parameters of neural networks.
  3. Recommender systems with Python
    We will explain how recommender systems can be easily implemented and validated in Python.
  4. Brief Description of the financial markets, data and neural network software
    Brief review of the financial markets, the type of data and the current software business and free use of neural networks
  5. Equity Applications (Modelling Stock Returns)
    Application cases will be reviewed in the stock markets
  6. Foreign Exchange applications (trading)
    They review applications of neural Models for Foreign Exchange Markets and trading operations
  7. Bond Applications (Rating)
    Be reviewed various applications of neural networks in Bond markets, especially the ratings.
  8. Macroeconomic Applications
    Will present various applications of neural networks in order macroeconomic prediction: IPC ...
  9. Corporate Performance (Business Failure Prediction)
    It will explain the various models of business failure and applications available neural models
  10. Presentations of companies
    Different companies will be invited to explain their applications in the field of AI

Activities

Properties of recommender systems

the student will work on the insight of the way that recommender systems work.
Theory
1
Problems
0
Laboratory
0
Guided learning
0
Autonomous learning
0
Objectives: 1 2
Contents:

Statistics of finance data and relationship to learning algorithms

The student will understand how the different properties of data can affect recommender systems.
Theory
1
Problems
0
Laboratory
0
Guided learning
0
Autonomous learning
0
Objectives: 2
Contents:

Data processing for using recommender systems

Understands the different effects of different types of data on the performance of the recommender systems.
Theory
1
Problems
0
Laboratory
0
Guided learning
0
Autonomous learning
0
Objectives: 3
Contents:

Applications of recommender systems (1)

Understanding the potential of AI in the industry
Theory
4
Problems
0
Laboratory
0
Guided learning
0
Autonomous learning
0
Objectives: 4
Contents:

Applications of recommender systems (2)

Understanding the potential of AI in the industry
Theory
3
Problems
0
Laboratory
0
Guided learning
0
Autonomous learning
0
Objectives: 4
Contents:

Examples of practical problems: companies

The student will observe business practice
Theory
0
Problems
11
Laboratory
0
Guided learning
0
Autonomous learning
0
Objectives: 5
Contents:

Teaching methodology

The teaching methodology is divided into three parts, the first is the exposure of theoretical concepts, the second in the visualization of the potential applications and thirdly presenting real case studies in business.

Evaluation methodology

The evaluation of the seminar has three parts. A first case study the issues associated with 1-3 with a weight of 40%, a second case study topics related to 4-9 with 40% and finally a summary of the presentations of companies with 20%.

Previous capacities

Interest in business and financial applications from the perspective of AI, especially in recommender systems