天美直播

This website uses cookies

The website of the Fundaci贸 Polit猫cnica de Catalunya uses its own and third-party cookies to improve the browsing experience and for statistical purposes. For more information about cookies you can consult the

Manage cookies
Allow all cookies
Campus
MY_TECH_SPACE


Go
Campus in maintenance
User and / or password incorrect
You have no active environment
Your access has been restricted. Consultation with the department of administration
Due to technical problems, the virtual campus is inaccessible. We are working to solve it. Sorry for the inconvenience.
You are not authorized to make this call. You can consult webmaster.fpc@fpc.upc.edu
You have exceeded the maximum number of attempts. Your user is temporarily blocked. Check back in a little while.
You must enter your campus username, not an email
You have to perform the verification to verify that you are not a robot.
Home   >  Master's & postgraduate courses  >  Education  >  Summer Course in Applied Machine Learning to Solve Real-World Problems
We advise you! Request information or admission
  • discount

    €300 discount for FME-UPC students

  • discount

    €250 discount for students from other UPC or UB schools, adjunct faculty from UPC or UB, and full-time faculty from UB not affiliated with the MESIO program

  • discount

    €200 discount for students from other universities

  • discount

    Free for full-time faculty at the UPC and MESIO UB or involved departments

Presentation

Edition
1st
Hours
15
Delivery method
Face-to-face
These courses will be conducted 'face-to-face' and will also be streamed live.


Language of instruction
English
Fee
€400
Notes payment of enrolment fee and 0,7% campaign
Registration open until the beginning of the programme or until end of vacancies.
Start date
Start date: 07/07/2025
End date: 11/07/2025
Timetable
Monday: 3:00 pm to 6:00 pm
Tuesday: 3:00 pm to 6:00 pm
Wednesday: 3:00 pm to 6:00 pm
Thursday: 3:00 pm to 6:00 pm
Friday: 3:00 pm to 6:00 pm
Taught at
Facultat de Matem脿tiques i Estad铆stica (FME)
C/ Pau Gargallo, 14. Edifici U.
Barcelona
Why this programme?
This course is part of the XVIII Summer School of the Master's degree in Statistics and Operations Research (MESIO UPC-UB).

Modeling with machine learning
is one of the most in-demand skills today, but its effective application in real-world environments—such as banking, finance, marketing, or technology—requires much more than mastering algorithms. This hands-on training is designed to solve real problems, from data acquisition and preprocessing to model implementation, calibration, and validation.

The course in Applied Machine Learning for Solving Real-World Problems offers a comprehensive view of the machine learning project lifecycle, combining theoretical foundations with practical experience in current tools such as regularized regression, decision trees (GBM, XGBoost, CatBoost), neural networks, and generative models (LLMs). Through practical examples and a Kaggle-style challenge, participants will learn to develop robust solutions and avoid common pitfalls in real-world projects.

Primarily intended for students of the MESIO master’s program. The seminars can be recognized with 3 ECTS if 2 courses are completed and passed, and with 5 ECTS if 3 courses are completed and passed, subject to approval by the Faculty of Mathematics.
Aims
  • To understand the challenges associated with creating models in real-world scenarios, from data acquisition to selecting the optimal model and validation methods tailored to specific problem types.
  • Promote good practices and provide insights into common issues encountered in large-scale modeling projects.
Who is it for?
Students interested in applying current Machine Learning techniques in a production environment. Graduates in mathematics, statistics, engineering and related quantitative fields. Students must bring their own laptops.

Students should have basic knowledge of algebra and statistics, as well as some programming experience (the course will be taught in Python).

Software Requirements
Python 3 will be the preferred tool for its ease of use and flexibility. Students may also use R if they feel more comfortable with it.

Training Content

List of subjects
15h
Applied Machine Learning to Solve Real-World Problems
Introduction to Modeling

  • Supervised vs. unsupervised learning
  • Supervised:
    • Classification
    • Regression 
  • Metrics:
    • Classification (AUC, Gini, AR, Somers' D, Kolmogorov-Smirnov...)
    • Regression (R^2, RMSE...)
  • Best modeling practices (train/test partition, cross-validation, overfitting control)

Feature Engineering

  • Data processing in real-life and Big Data. Common errors in data management (e.g., future information and data leakage)
  • Handling missing values (mean/median/percentiles, control dummy, K-Nearest Neighbors...)
  • Treatment and creation of new features (categorical variables, Weight of Evidence/continuous bucketization, dummies and one-hot encoding, alert counters...)

Models and Applicability Cases

  • Basic problem examples:
    • Ratings in credit risk (classification)
    • House prices (regression)
    • Image recognition (classification)
  • Linear models (OLS/Logistic) and regularization (LASSO, RIDGE, ElasticNet)
  • Decision trees and random forests
  • Gradient Boosting (GBM, XGBoost, LGBM, CatBoost)
  • Neural networks (1D & 2D CNN) for text and image processing
  • Generative AI and Large Language Models (LLM):
    • APE (Automatic Prompt Engineering)
    • LLM prompting instead of rules
  • Stacking techniques
  • Parameter optimization (hyperparameter tuning)
  • Feature interpretation in black-box models using SHAP (effect of removing/adding each feature)
  • Using LLMs for explanations

Calibration of Classification Models

  • Need for calibration
  • Confusion matrix and pay-off methodology
  • Basic calibration techniques of the probability curve (Platt scaling/binomial model, isotonic regression, Bayesian central trend correction)
  • Advanced calibration techniques of the probability curve (Tasche: "The art of probability-of-default curve calibration")

Model Validation

  • Stability
  • Performance

Model Development in a Real Case and Kaggle Evaluation Contest

  • Building a classification model from scratch to predict the probability of default for corporations
Degree
Certificate issued by the Fundaci贸 Polit猫cnica de Catalunya.

Learning methodology

The teaching methodology of the programme facilitates the student's learning and the achievement of the necessary competences.

The course will be structured as a combination of theoretical classes and practical exercises to ensure a solid understanding of the different concepts and methodologies. In addition, debates and interactions will take place.
Virtual campus
The students on this summer course will have access to the My_ Tech_Space virtual campus - an effective platform for work and communication between the programme's students, lecturers, directors and coordinators. My_Tech_Space provides the documentation for each training session before it starts, and enables students to work as a team, consult lecturers, check notes, etc.

Teaching team

Academic management
  • Langohr, Klaus
    info
    /
    PhD in Statistics from the Polytechnic University of Catalonia (UPC). Graduate in Statistical Sciences and Techniques from the University of Dortmund (Germany). Associate professor at the Department of Statistics and Operations Research of the UPC.
Teaching staff
  • Moragas Vilarnau, Jordi
    info

    PhD in Mathematics (specialization in Combinatorics, Graph Theory and Aditive Number Theory) from the Polytechnic University of Catalonia (UPC), and Postgraduate in Quantitative Techniques for Financial Markets also at the UPC.

    Currently, Head of Data Science at the N26 bank in Berlin (Germany), leading the department in the prototyping, development and deployment of advanced Machine Learning models in the areas of credit risk, prevention and detection of financial crime, and the authorization of credit card transactions.

Request information or admission

Information and guidance:
Isabel de la Fuente Larriba
(34) 93 115 57 51
Request received!
After we have registered your request, you will receive confirmation by email and we will be in touch.

Thank you for your interest in our training programmes.
Error
Due to an error in the connection to the database, your submission has not been processed. Please try again later, phone us on (34) 93 112 08 08, or send us an email at: webmaster.fpc@fpc.upc.edu
You have exceeded the maximum size of the file
Please check your payment details. The platform has returned an error.
You can make the payment again without re-entering the data.

Name:

Programme: Applied Machine Learning to Solve Real-World Problems

Fee: €400

Submit and make the payment
  • If you have any doubts.
  • If you want to start the registration procedure.
How to start admission
To familiarise yourself with the registration process for this programme, please contact:

Isabel de la Fuente Larriba
(34) 93 115 57 51
isabel.delafuente@talent.upc.edu




  date protection policy

* Mandatory fields

Basic information or first layer on data protection

Controller

Fundaci贸 Polit猫cnica de Catalunya (FPC).

Purpose of processing

Respond to requests for information from the data subjects on training activities managed or carried out by the FPC.

Establishment or maintenance of the academic relationship with the data subject.

Send information on the activities of the FPC.

Legitimation

Data subject's consent.

Legitimate interest in the development of the academic relationship.

Addressees

No assignments or communications.

Rights

Access, rectification, erasure, restriction, object and data portability.

Data protection officer contact details

info.dpo@fpc.upc.edu

Additional information

Privacy policy of our website.

Storage limitation

Privacy policy of our website.

Payment services

In the event that the data subject enters into a formal relationship with the FPC, the data subject authorises and consents to the charge, thereby expressly waiving the right to a refund of the charge.

ACADEMIC AND ECONOMIC REGULATIONS

The Fundaci贸 Polit猫cnica de Catalunya reserves the right to modify content, price, location, timetable and dates prior to the start of the course. Registration on the course will not be confirmed until payment has been made.

Registration rights. The interested party must make payment of the specified registration fee for the course. This fee will be deducted from the full course fee and will only be reimbursed if the applicant is not admitted.

Cancellation or deferment.The Fundaci贸 Polit猫cnica de Catalunya reserves the right to cancel or defer a course if the minimum number of students is not met. In case of cancellation or non-admittance, the Fundaci贸 Polit猫cnica de Catalunya will return all amounts paid in full, without any additional compensation. In case of deferment, applicants may request reimbursement of fees paid.

Cancellation of registration.
In the event of withdrawal or cancellation of the registration, the student must notify the UPC School in writing beforehand.
  • If this request for cancellation is made 45 days before the start of the programme, the UPC School will retain only 30% of the total registration fee and refund the difference paid.
  • In the event that the application request is made within 45 calendar days and the beginning of the programme, the UPC School will retain 60% of the registration fee.
  • No applications for refunds may be made after the programme has started.
Under exceptional circumstances, refunds of the registration fee will be made if the student's cancellation is due to one of the following circumstances:
  • Denial of a visa, subject to submission of supporting documentation. In this case, the UPC School will refund the registration fee less 300 Euros for administrative expenses.
  • Serious illness or accident accredited by an official medical certificate, stating the start date of the illness and the anticipated convalescence period. In this situation the UPC School's decision will be as follows:
    • If the notification takes place up to one month after the start of the programme, it will refund the amount actually paid, less 300 Euros as administrative expenses.
    • No refunds will be made after a month after the start of the programme. It will be only be possible to use the amount paid as a deposit for the registration fee of the next programme. This procedure entails no administrative fee for the student. The price difference between the new registration fee and the amount previously paid will be payable by the student under all circumstances.

Changes in registration. Any changes in registration, previously authorised by the Fundaci贸 Polit猫cnica de Catalunya, will incur a 300 € administration fee.

Discounts.
  • Discounts are non-accumulable. The greater discount of those requested will be applied.
  • Discounts can only be applied under prior application and approval.
  • Once registration has been confirmed, no discount will be applied.
  • Students are responsible for placing applications for any discounts.

Qualification. In order to obtain the Qualification/Diploma issued by the Polytechnic University of Catalonia, the student must be in possession of a recognised university qualification or internal university qualification equivalent to a degree or diploma. If this is not the case, the student will receive a certificate of completion for the course, issued by the Fundaci贸 Polit猫cnica de Catalunya. Students with outstanding payments due to the Fundaci贸 Polit猫cnica de Catalunya or who has not approved all the credits necessary to overcome the program before the date of completion of this program will not be eligible to receive any qualification, diploma or certificate.

Barcelona, October 31, 2017


Send