From stock investing to financial analysis and econometrics, financial engineering has the potential not only to improve spending, saving, and investing decisions for the future but also to make possible the development of new products, services, and markets.
At ESILV, financial engineering projects are part of the curriculum that develops graduates who can create innovative solutions for real financial problems, using state of the art analytical techniques and computing technology. Here are three projects developed by ESILV students, as part of their 5-th year industrial innovation projects, that bring real value in corporate finance, investments and financial accounting.
Systemic Collar Strategy
“First of all, we had to truly understand the title of the subject before we could fully embark on it. A systemic collar-type strategy corresponds to the sale of an option (call) on a systemic basis (every month, for example) on an underlying asset, which in our case was the Eurostoxx50.”
The aim of the project was to implement a financial investment strategy that is self-financing thanks to the premium of the option sale. Firstly, the team had to determine their strategy with the help of our partner. Secondly, having the strategy in place, they have opted for a mathematical formalism that allowed them to build their model, then to implement it electronically, to carry out their tests and advance the back-test.
“Our model allows us to follow the evolution of our portfolio on each date. That’s a combination between the premium of the call at a risk-free rate and the call’s value at all dates. The value of the portfolio then allows us to calculate the PnL of the strategy, its performance and to compare it to the index itself. Finally, we set up the strategy by implementing it on Python.”
Thus, the students can follow the evolution of their strategy regarding the PnL performed, and the performance achieved.
Also, it enables them to vary the parameters of the strategy, such as the strike or the maturity of the call. They can also compare them. They calculate different ratios such as the Max Drawdown, the information ratio and the Sharpe ratio giving us additional pieces of information on the robustness of the strategy.
I.A.C.A: Intelligent Automated Comparable Analysis
“The problem we have observed is that actually there are very few tools that allow us to perform free analyses, or to collect data that will enable us to compare companies in the same sector of activity, in terms of their economic efficiency. Moreover, none of them allows for an intelligent classification of this data.”
Thus, the team has developed a tool to make an accounting analysis as complete and optimized as possible using Machine Learning and clustering integration. The latter therefore allowed them to compare companies which belong to the same sector of activity, of similar size, with similar growth and turnover.
The user can then make comparisons on the financial health of companies belonging to the same group to assess which have performed best and their potential future projections. The analysis is based on a “home-made” algorithm taking into account different financial ratios.
The company database is derived from Bloomberg and the user has access to more than 1,000 listed companies. All this is accessible from our website iaca-tool.com. “Beyond a school project, we wanted to transform our PI2 into a real financial analysis tool available to all.”
AI: Regime Switching Models in Finance
Deep Learning is a field of study of artificial intelligence that allows automatic learning based on an extensive database. It has only recently (2010) been democratised in more and more areas, namely market finance. It helps to evaluate the risks that a company would take before making an important decision or to predict a company’s share price. The project focused on how to build a long term strategy on regime-switching models, such as signal timing, using deep learning.
“Our research has mainly covered the field of statistics as well as probabilities. We were able to apply these new concepts during our tests, primarily concerning moving averages, as well as the Markov regime in the American stock market. Once we completed the mathematical research for our project, we also had to improve our skills in the field of programming (Python). So, we had to learn how to use the PyTorch library.”
The study of this open-source deep-learning library required the study and research of predictive modelling with deep learning in finance. “We were able to optimise our algorithms and future Machine Learning prediction programs.”