Suggestions
Ivan Blanco
Professor at CUNEF - Investment Advisor at NOAX GLOBAL, FI
Dr. Iván Blanco is an Assistant Professor at CUNEF and the Founder & Director at NOAX with a rich research background in finance and economics.
His research work has been published in esteemed journals such as "Journal of Financial Economics", "Journal of Corporate Finance", "The Energy Journal" and "Applied Sciences". He has also presented his work at prestigious conferences like EFMA and GSE Economics.
Dr. Blanco's research interests include Artificial Intelligence, Machine Learning, Technology, Asset Pricing & Quantitative Investments, and Feedback effects between Financial Markets and the Real Economy.
He holds a Ph.D. in Finance with honors from Universidad Carlos III de Madrid and has a strong educational background including an MSc in Finance and Quantitative Methods, an MBA in International Business, and a BSc/MSc in Aerospace Engineering.
With a diverse organizational history, he has served in various roles such as Fund Investment Advisor at NOAX GLOBAL, Adjunct Professor of Financial Engineering at WorldQuant University, and as a Senior Quant Researcher/Trader at Arfima Trading.
Dr. Blanco's experience also includes positions at top financial institutions like BBVA España and Banco Santander, showcasing his expertise and versatility in the finance and technology sectors.
Throughout his career, he has been an active contributor to academia and industry, blending his expertise in finance, technology, and quantitative methods.
Highlights
📢 New Trading Ideas! "Deep Learning for Options Trading: An End-To-End Approach".....Keep reading! 🔻
The paper introduces a nice ML strategy for options trading, moving beyond traditional market dynamics and option pricing models by employing a fully integrated neural network framework.
The main contributions and findings are as follows:
👉 The study presents an end-to-end neural network that directly learns optimal trading decisions from market data, bypassing the need to predict option returns or simulate market processes. This approach is specifically applied to a portfolio of delta-neutral equity options.
👉 Backtesting results over a decade reveal that deep learning models, particularly Linear and LSTM models, significantly outperform traditional trend-based strategies, achieving Sharpe ratios as high as 1.329.
👉 The research further shows that incorporating turnover regularization enhances model performance, maintaining profitability even under high transaction costs, thereby proving the robustness and efficiency of this innovative approach.
→ Join 3000+ Asset Pricing & Quant Finance enthusiasts who receive top new research ideas weekly in their email: https://lnkd.in/dkxSDJpq
Link to the paper: https://lnkd.in/dySVsshW
📢 How do you combine classical portfolio optimization with Deep Learning? Keep reading to get some insights from this paper 👇
The paper presents an interesting approach that combines portfolio optimization with deep learning by enabling portfolio weight functions of any complexity.
My takeaways from the paper (links at the end of the post):
➡ The paper generalizes the parametric portfolio policy framework by integrating deep neural networks, enabling portfolio weight functions of any complexity. This advanced approach markedly increases investor utility, with models showing a substantial improvement in monthly certainty equivalent returns by 75 to 276 basis points over traditional linear policies.
➡ It highlights the critical role of risk aversion as a regularization parameter in these models, effectively balancing the complexity of the model against economic motivations. This finding illustrates the delicate interplay between model sophistication and investor risk preferences.
➡ The study also demonstrates that the complex, network-based portfolio policies not only enhance the relationship between investor utility and firm characteristics but also adapt well to realistic trading conditions. These include various constraints such as short sales, weight restrictions, and transaction costs, maintaining robust performance across these settings.
➡ The Deep Parametric Portfolio Policy (DPPP) model, introduced in the paper, excels in handling flexible, non-linear relationships between portfolio weights and stock characteristics. This model is designed to accommodate different utility functions and manage leverage or portfolio weight constraints effectively.
➡ Overall, the findings challenge the traditional risk-return tradeoff, suggesting that complex model strategies like DPPP can lead to higher returns without increasing risk exposure. This approach provides a sophisticated tool for asset managers seeking to optimize portfolios in a nuanced investment landscape.
→ Join 2500+ Quants who receive new trading ideas weekly in their email: https://lnkd.in/dkxSDJpq
Link to the paper: https://lnkd.in/dC8VTMpb
