Shaun Comfort’s Post

Embark on a captivating journey into the realm of sensitivity analysis with our project, where we unravel the intricacies of decision-making processes. Delve into the core principles of sensitivity analysis, understanding how variations in input parameters impact the outcomes of complex models. This project not only introduces the fundamental concepts but also guides you through practical applications, empowering you to assess the robustness and reliability of your decisions in diverse scenarios. Gain valuable insights into the art of making informed choices by comprehending the sensitivity of your models to changes – an indispensable skill for analysts, researchers, and decision-makers alike.

New Preprint 🚨: In this paper, my brilliant PhD student, Man Yiu (Tim) Tsang, and I introduce a new data-driven trade-off (TRO) approach for modeling uncertainty. Our approach serves as a middle ground between the optimistic approach, which adopts a distributional belief, and the pessimistic approach, which hedges against distributional ambiguity. It allows decision-makers to obtain a spectrum of decisions, ranging from optimistic to conservative decisions. In addition, it has desirable finite sample and asymptotic properties. More details in the paper https://lnkd.in/emsMCBQe #optimizationunderuncertainty #robustoptimization #stochasticprogramming #DRO #biasanalysis #asymptoticproperties #conservatism #operationsresearch

Inspiring Learning Experience in Time Series Analysis and Forecasting As part of my quantitative finance course, we recently started exploring Time Series Analysis and Forecasting with some models. I had trouble understanding the need for stationarity, so I turned to YouTube for explanations. Voila! I came across this incredible 4-hour+ lecture on Time Series Analysis and Forecasting by Dr. Abhinanda Sarkar. Initially, I planned to watch just 15-20 minutes at 2X speed to see if it answers the query that I have, but I was so impressed that I slowed down the video and focused on his insights. Dr. Sarkar’s enthusiasm and clarity of thought were truly inspiring. He effortlessly established key concepts and answered numerous questions with ease, making complex topics accessible and engaging. Over a couple of days, I finished watching the entire lecture and I’m still amazed at how engaging it was. This is what a good teacher does—takes a complex topic, breaks it down into manageable chunks, and explains it in a way that stays with you for a long time. If you’re looking to deepen your understanding on the topic, I recommend checking out this video - https://lnkd.in/eBRrX6ui. Disclaimer: I have no affiliations with Great Learning or Dr. Sarkar. #TimeSeriesAnalysis #Forecasting #QuantitativeFinance #Learning #Education #Inspiration #Finance #StayCurious

🌟 Exciting news! Join us for the next #AMLEDS #webinar on Friday, April 19th at 11 AM EDT / 4 PM BST / 5 PM CEST with David Rapach from the Federal Reserve Bank of Atlanta. 🎓 He'll discuss "The Anatomy of Machine Learning-Based Portfolio Performance" alongside Philippe Goulet Coulombe, Christian Montes Schütte, and Sander Schwenk-Nebbe. 🔍 Moderated by Daniele Massacci from King's College London. 📚 Summary: This paper explores the economic value generated by #return #predictability in #machinelearning models using #Shapley values. The paper delves into the intersection of machine learning and #portfolio performance, focusing on generating return #forecasts and constructing portfolios based on firm characteristics. Dive into the implications of #investment strategies and join us for an insightful discussion! 🚀 Register now: https://lnkd.in/egTakd2 📃 Link to the paper: https://lnkd.in/epNjidy9 #EconLinkedin #EconTwitter #MachineLearning #AMLEDSWebinar #AssetReturnPredictability #PortfolioConstruction Let's unravel the mysteries of machine learning in economics and data science together! 🌐✨ #KnowledgeSharing #ResearchInFocus #InvestmentInsights

Forecasting: Principles and Practices 📈💡 In our data-driven world, forecasting is the superpower we all seek - and this book is the ultimate guide to mastering it! 📊 From historical data to future predictions, it's a step-by-step roadmap to harnessing the power of time series analysis. With tools like R programming, we can unlock invaluable insights from our data, giving us the edge to tackle the unknown with confidence. 💪 Whether you're in aviation, business, finance, science, or beyond, forecasting opens doors to informed decision-making and strategic planning. Dive into this intellectual gold mine and unlock a world of possibilities! 🌟✨ #Forecasting #DataAnalysis #RProgramming #PredictiveAnalytics #FutureInsights

📢 Exciting News! Our latest blog post explores the fascinating concept of Subjective Causality. We delve into how decision makers' subjective causal judgements can be identified through their preferences over interventions. Drawing on established theories, we reveal how causal models can illuminate uncertainty and utility in decision-making. Dive into the details here: https://bit.ly/3S6kW8F [econ.TH]

An insightful contribution in the field of scenario analysis.

Hi. We have launched a new scenaring method called Principal Component Analysis which belongs to the scenario methods tradition that I´ve called "Assessment into numbers and into algorithm methods (ANAM)". It is basically a mixed scenario method, where human centric-assessment is broken into decomposition e.g. correlation analysis table and usually into numerical form that is again used in an algorithm to model higher probability, logical, coherent, credible and less bias scenarios. The other examples of this scenaring tradition are e.g `La Prospective´, ‘Multiple Correspondence Analysis’ and `OLDFAR´. This tradition, together with the first scenaring tradition called either `econometric´ or `predictive´ where only hard numbers are crunched and modelled, can be regarded as the two different forecasting traditions of the futures studies. The third main scenario tradition is naturally the fully qualitative Intuitive Logic method which we used to use much in Futures Platforms scenario analysis before the PCA was taken into use. #foresight #scenario #scenarioplanning #futuresstudies #futuresintelligence

💡 “Every decision is made within a feedback loop. The decision controls action which alters the system levels which influence the decision. A decision process can be part of more than one feedback loop.” - Jay Wright Forrester, the Father of the field of System Dynamics In Principles of Systems, Professor Forrester explains the basic principles behind system behavior. He introduces the concepts of structure and dynamic behavior that were first introduced in his prior books, Industrial Dynamics (1961) and Urban Dynamics (1971). 📗 Grab a copy: https://ow.ly/vGHR50Qq1L1 📗 Check out Jay’s classics: https://ow.ly/zSul50Qq1L4 #SystemDynamics #systemsthinking #bestseller

Thrilled to share our latest paper: Multifractality approach of a generalized Shannon index in financial time series! This paper introduces a generalized Shannon index (GSI) and demonstrates its application in understanding system fluctuations. To this end, traditional multifractality approaches are explained. Then, using the temporal Theil scaling and the diffusive trajectory algorithm, the GSI and its partition function are defined. Next, the multifractal exponent of the GSI is derived from the partition function, establishing a connection between the temporal Theil scaling exponent and the generalized Hurst exponent. Finally, this relationship is verified in a fractional Brownian motion and applied to financial time series. Special thanks to professors Juan E. Trinidad Segovia, Miguel A. Sanchez-Granero, and Carlos José Quimbay Herrera.