| Titre : | Machine Learning in financial Credit Risk Assessment | | Type de document : | projet fin études | | Auteurs : | IDRISSI Abdellatif / SAFRAOUI Majdouline, Auteur | | Langues : | Français (fre) | | Catégories : | Ingénierie Finance et la Gestion des Risques (IFGR)
| | Index. décimale : | mast 134/18 | | Résumé : | In recent years, machine learning has been the buzzword in algorithmic trading and quantitative business. The financial markets were one of the first followers of Machine Learning (ML).
This thesis focuses on the use of machine learning in credit risk assessment which is a general term used by financial institutions to describe the methodology used to determine the probability of a loss on an asset, an investment or a particular loan.
The purpose of the credit risk assessment is to determine whether an investment is worthwhile, what steps should be taken to mitigate the risk, and what the rate of return should be to make an investment. This is why it is essential to create a credit risk forecasting model as specific as possible, as it allows the institution to provide fair prices to customers while ensuring predictable and minimal losses.
The treatment of this subject will be done in two parts, one which is theoretical and which presents the Machine Learning, the different methods of statistical classification and learning used by ML, etc. and a practice where we will apply these different methods of classification and learning.
Our development and modeling part is built in Python. We combine the use of machine learning algorithms with the visualization of data to better understand the variables of our data by taking a database which we will use a methodology that allows to measure the performance of these algorithms to obtain the best prediction results that will be compared at the end of this project. |
Machine Learning in financial Credit Risk Assessment [projet fin études] / IDRISSI Abdellatif / SAFRAOUI Majdouline, Auteur . - [s.d.]. Langues : Français ( fre) | Catégories : | Ingénierie Finance et la Gestion des Risques (IFGR)
| | Index. décimale : | mast 134/18 | | Résumé : | In recent years, machine learning has been the buzzword in algorithmic trading and quantitative business. The financial markets were one of the first followers of Machine Learning (ML).
This thesis focuses on the use of machine learning in credit risk assessment which is a general term used by financial institutions to describe the methodology used to determine the probability of a loss on an asset, an investment or a particular loan.
The purpose of the credit risk assessment is to determine whether an investment is worthwhile, what steps should be taken to mitigate the risk, and what the rate of return should be to make an investment. This is why it is essential to create a credit risk forecasting model as specific as possible, as it allows the institution to provide fair prices to customers while ensuring predictable and minimal losses.
The treatment of this subject will be done in two parts, one which is theoretical and which presents the Machine Learning, the different methods of statistical classification and learning used by ML, etc. and a practice where we will apply these different methods of classification and learning.
Our development and modeling part is built in Python. We combine the use of machine learning algorithms with the visualization of data to better understand the variables of our data by taking a database which we will use a methodology that allows to measure the performance of these algorithms to obtain the best prediction results that will be compared at the end of this project. |
|
Faire une suggestion Affiner la recherche
Machine Learning in financial Credit Risk Assessment / IDRISSI Abdellatif / SAFRAOUI Majdouline
