Построение скоринговых моделей с использованием методов машинного обучения

Магистратура 2021/2022

Статус: Курс по выбору (Бизнес-аналитика и системы больших данных)

Направление: 38.04.05. Бизнес-информатика

Кто читает: Департамент бизнес-информатики

Где читается: Высшая школа бизнеса

Когда читается: 1-й курс, 2, 3 модуль

Формат изучения: без онлайн-курса

Охват аудитории: для своего кампуса

Преподаватели: Мунерман Илья Викторович

Прогр. обучения: Бизнес-аналитика и системы больших данных

Язык: английский

Кредиты: 5

Контактные часы: 40

Full Syllabus

Abstract

The main aim of this course is a species of different country data sets and technics for integration this data for common international data environment. It also considers the features of algorithms for use online data for the instant response of the model to changing environmental circumstances, taken into the consequences of a pandemic. The course is designed for listeners which known elementary economics, finances, IT and mathematics and may be able for economists, IT specialists, managers, include MBA and journalists.

Learning Objectives

Ability to use modern methods and relevant information technologies to formulate and solve fintech problems
Data-driven services marketing skills
Ability to estimate the performance of financial decisions based on modern models and computer programs
Knowledge of the types of modern scoring systems, methods of their design and data sources
Ability to use data mining and machine learning methods to solve applied problems.
Ability to design business models based on intelligent IT services

Expected Learning Outcomes

Be able to calculate corrections to scoring models depending on the purposes of their construction, calculate credit limits, adjust the probability of occurrence of various events.
Be able to form a scoring line for solving a specific task of the subject of economic activity.
Be able to formulate and correctly interpret definitions of concepts, terms and categories used in the development of scoring models.
Be able to organize comprehensive counterparty scoring, including monitoring of the dealer network and potential customers, develop recommendation systems and calculate the functional value of complex assets.
Be able to quickly recognize problems and find the scoring model needed to solve it.
Be able to solve problems of building machine learning models using modern software.
Demonstrate the ability to solve design and economic problems in professional activity.
Demonstrate the mastery of Fintech tools.
Know the algorithms of recommendation systems and black box interpreters.
Know the basic machine learning tools.
Know the basic methods of scoring work in a large company or marketplace.
Know the differences between due diligence, financial risk indices and comprehensive credit scoring.
Know the main approaches to building scoring systems based on modern financial concepts, such as methods of residual income, claim burden, payment discipline indices, etc.
Know the main types of scoring ratings, etc. common features and differences between them.
Know what problems scoring models solve.
Master the methods of Big Data analysis used to solve professional tasks at the micro, meso and macro levels, including at the level of the financial market.

Course Contents

Contemporary financial analyses main challenges
Big data, data mining, data science
Main data types
Correlation
Data processing. Modeling
Estimation and model testing
Interpretable models and recommendation systems
Applications

Assessment Elements

Home assignments
Case disscussions
When preparing for discussions in practical classes, it is necessary to use not only lecture material, educational literature, but also regulatory legal acts and materials of law enforcement practice. Theoretical material should be correlated with legal norms, since changes and additions may be made to them, which are not always reflected in the educational literature
Kaggle contests
During the course, three closed championships are held in Kaggle, on the construction of scoring models of the value of real estate, the probability of default and another one in agreement with the level of students
Final exam

Interim Assessment

2021/2022 3rd module
0.2 * Case disscussions + 0.25 * Kaggle contests + 0.25 * Home assignments + 0.3 * Final exam

Bibliography

Recommended Core Bibliography

Bernd Engelmann, & Ha Pham. (2020). Measuring the Performance of Bank Loans under Basel II/III and IFRS 9/CECL. Risks, 8(93), 93. https://doi.org/10.3390/risks8030093
Brooks,Chris. (2019). Introductory Econometrics for Finance. Cambridge University Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsrep&AN=edsrep.b.cup.cbooks.9781108422536
Greenwald, A., Nosek, B., & Banaji, M. (2016). Understanding and Using the Implicit Association Test: 1. An Improved Scoring Algorithm. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.4AB789A7
Ian Goodfellow, Yoshua Bengio, & Aaron Courville. (2016). Deep Learning. The MIT Press.
Siddiqi, N. (2017). Intelligent Credit Scoring : Building and Implementing Better Credit Risk Scorecards (Vol. 2nd edition). Hoboken, New Jersey: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1441143

Recommended Additional Bibliography

Gareth James, Daniela Witten, Trevor Hastie, & Robert Tibshirani. (2013). An Introduction to Statistical Learning : With Applications in R. Springer.
Trevor Hastie, Robert Tibshirani , et al., The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edition, 2017. Free from the publisher: https://web.stanford.edu/~hastie/ElemStatLearn/printings/ESLII_print12.pdf

Course Syllabus