- Docente: Pietro Rossi
- Credits: 6
- Language: English
- Teaching Mode: Traditional lectures
- Campus: Bologna
- Corso: Second cycle degree programme (LM) in Quantitative Finance (cod. 8854)
Learning outcomes
The student is exposed to selected frontier issues of research from scholars in each field. Each scholar will address a topic, starting from the basic principles to the frontier questions. From the workshop, the student will collect ideas for his thesis and interests driving him to his future career.
Course contents
The course is divided into lectures given by external professors or experts in a field. These are the specific contents this year:
Giovanni Della 3H: Introduction to ML
* What is Machine Learning all About
* Supervised and Unsupervised Learning
* Python & R Ecosystem for ML
* What is Unsupervised Learning
* When to use it and how it work
* K-means clustering
Flavio Cocco 6H: Introduction to SciKit-learn
* Naive Bayes
* Logistci Classification
* Decision Tree
* Random Forest
* Boosting
Giovanni Della Lunga 6H: Text Analytics
- Introduction to text mining: background and motivations
- Text Mining with R
- Natural Language Processing with Python
- Loading Texts
- Text pre-processing
- Stemming
- The Document Term Matrix
- Mining the Corpus
- Simple Clustering Techniques
- What is Sentiment Analysis
Pietro Rossi 4H: Principles of Neural networks
* Fundamental theorems of machine learning
* Introdution to statistical pattern recognition
* Perceptron
* Curse of dimensionality
* Neural Network
* Back Propagation
Pietro Rossi 3H: Examples from literature on pricing using NN
* Deep Learning Profit and Losses
* Deep Learning Pricing ( Portfolios, Heston, IR derivatives )
Priscilla Palacio Ruiz 6H: Neural network classification, an example
Emulation of Issuer Credit Ratings in the Banking Sector
* Data preprocessing for Machine Learning:
- Dealing with Missing Values in Financial Data:
* Multiple Imputation by Expectation Maximization with Bootstrapping [ R ]
* Feature Selection with Scikit - learn [ Python ]
* Deep Learning for classification with Tensor flow and Keras [ Python ]:
- LSTM -Long Short Term Memory- Neural Networks.
- Deep Learning Ensembles.
Readings/Bibliography
Christopher D. Manning and Hinrich Schutze
- Foundations of Statistical Natural Language Processing
Stuart Russel and Peter Norvig
- Artificial Intelligence. A modern approach
Christopher M. Bishop
- Neural Network for Patter Recognition
SciKit learn Tutorial
https://scikit-learn.org/stable/tutorial/index.html
The Python Tutorial
https://docs.python.org/3/tutorial/
Teaching methods
Students might be asked to implement some software on their own devices, i.e. laptops or pcs.
Assessment methods
Attendance is mandatory, at least 75% of all classes is necessary and will be verified. Students will be asked to write a report on one each of the topics.
Teaching tools
Usual tools in classical theoretical classes.
Office hours
See the website of Pietro Rossi
SDGs
This teaching activity contributes to the achievement of the Sustainable Development Goals of the UN 2030 Agenda.