Machine Learning at EDHEC: A Hands-On Experience in the Financial Engineering Master Programme

As financial markets become increasingly complex, the role of machine learning (ML) in Finance has never been more critical. EDHEC Business School’s MSc in Financial Engineering provides students with cutting-edge exposure to these advanced techniques, equipping them with the necessary skills to navigate modern financial challenges. One key highlight of this programme is the Machine Learning Workshop, an intensive and hands-on module designed to integrate Machine Learning concepts with real-world financial applications.

We spoke with Ndeye Arame, a current student in the programme, about her experience in the module and how it has shaped her understanding of Machine Learning in Finance.

A Deep Dive into Machine Learning

The Machine Learning workshop was an immersive experience designed to provide students with a strong foundation in both supervised and unsupervised learning techniques. "The module was an intensive and hands-on introduction to machine learning concepts," explains Ndeye Arame. "The sessions combined theory with practical applications using Python libraries such as Scikit-learn. We covered all the supervised learning algorithms and some unsupervised learning algorithms like K-means, Agglomerative Clustering, and PCA."

One of the key takeaways from the workshop was the application of machine learning models to real-world financial problems. "What stood out the most to me was the clear link between machine learning models and their practical implementation in finance," she notes. "For example, logistic regression can be applied to binary classification problems such as credit risk assessment, while decision trees can be used for trading strategy optimisation."

One particularly memorable takeaway was seeing how cross-validation techniques improve model accuracy by mitigating overfitting—an essential concept in financial modelling. “One scenario that resonated with me was predicting loan defaults using a logistic regression model. It was fascinating to see how specific features like income level and credit score contributed to the model’s predictions,” she adds.

Real-World Applications and Key Learnings

The purpose of the workshop was to equip the MSc in Financial Engineering students with the ability to apply Machine Learning techniques to financial problems. "Key goals included understanding data preprocessing, model selection, cross-validation, and performance evaluation," says Ndeye Arame. "By the end, we were expected to confidently complete an end-to-end Machine Learning task, including feature engineering, model fitting, and interpreting results."

This practical approach helped reinforce essential programming skills and problem-solving strategies. "This module helped me reinforce my programming skills in Python and showed me how to approach complex financial problems systematically," she shares. "It also made me interested in further applications of Machine Learning, such as deep learning models that can predict stock prices and market movements by identifying patterns in historical and real-time data."

A key opportunity to apply these skills further is through the Applied Master Project in Algorithmic Trading, which challenges students to implement machine learning models in a real-world trading context. “The Applied Master Project in Algorithmic Trading is a great way to apply what we learned in the Machine Learning module. It’s both challenging and exciting to work on real financial problems,” Ndeye Arame shares.

Exploring Equity Derivatives: The Derivatives Bootcamp

In addition to machine learning, students in the MSc in Financial Engineering also participate in specialised workshops like the Derivatives Bootcamp, which was later expanded into a full module on Equity Derivatives. This bootcamp focused on advanced topics such as the Black-Scholes model, Greeks, the volatility surface, and volatility derivatives.

"The sessions were designed to provide both theoretical insights and practical interview questions for sales/trading roles," Ndeye Arame explains. During the bootcamp, students engaged in hands-on exercises, including:

• Derivation of the Black-Scholes PDE and its solutions for European options.
• Mathematically deriving and interpreting Greeks like Theta, Rho, and Vega.
• Simulating Delta hedging strategies.
• Analysing historical volatilities to construct implied volatility surfaces.

This rigorous training complements the broader financial engineering curriculum and provides essential skills for students aspiring to work in trading roles. "The bootcamp deepened my understanding of derivative pricing and risk management," she notes. "It aligns perfectly with my career aspirations in trading, where these concepts are applied daily."

Impact on Career Aspirations

Beyond enhancing technical skills, the Machine Learning module has influenced Ndeye Arame’s career perspective. "This module emphasised the growing importance of machine learning in finance, particularly for roles in quantitative analysis and trading," she states. "It motivated me to further explore Machine Learning techniques like neural networks, which have applications in algorithmic trading and portfolio optimisation."

Additionally, the workshop integrates with other coursework in the MSc in Financial Engineering. "The hands-on Python programmeming helped with other courses, such as quantitative portfolio management and advanced derivatives," she adds. "My knowledge of Python programmeming, mathematics, and statistical analysis was directly applied, reinforcing my understanding of regression analysis, a topic covered in our econometrics coursework in Master 1."

Key Takeaways for Future Professionals

The insights gained from the Machine Learning workshop will serve students well in their future careers. "The insights I will carry forward from this experience are: always preprocess data meticulously before model training, use cross-validation to fine-tune hyperparameters and minimize overfitting, and evaluate models on multiple metrics to understand their strengths and weaknesses," Ndeye Arame highlights.

EDHEC’s MSc in Financial Engineering, ranked #6 worldwide in the Financial Times 2024 continues to evolve, ensuring students receive top-tier quantitative training. The Machine Learning workshop is just one of many initiatives designed to equip future financial professionals with the necessary skills to thrive in an increasingly data-driven world. For students looking to develop expertise in quantitative finance, EDHEC offers a robust, hands-on approach to learning, setting graduates up for success in competitive financial roles. Learn more about the programme.