Q4-2021 FDP Exam: Registration is now closed |
Our webinars will boost your expertise in the latest trends in the industry and share insight into the FDP charter. Have a recommendation for an industry related topic, an author we should invite, an article you want to learn more about? Contact us: info@fdpinstitute.org. |
WEBINAR RECORDINGS & SLIDE DECKS |
Alternative Data and Collective Intelligence Investing: Date: March 8, 2021 Description: Over the last five years, the volume of information available to all has skyrocketed, leading to increased investor interest in alternative data or crowdsourced investment strategies. While opportunities for added value may be present, adoption also comes with a number of risks, both for early and late adopters. Join this conversation as readings from the 2021 Financial Data Professional (FDP) curriculum are brought to life.Panelists: Doug Dannemiller, Head of Investment Management Research, Deloitte Center for Financial Services; Sean Collins, Research Manager, Deloitte Center for Financial and Services and Aaron Filbeck, CAIA, CFA, CIPM, FDP, Director, Global Content Development, CAIA Association. |
Scaling AI Deployments: Opportunities and Challenges Date: October 16, 2020 Description: Nicolaus Henke, Sr. Partner, McKinsey & Co; Jane Buchan, CEO of Martlet Asset Management; and Bill Kelly, CEO of CAIA speak with Dr. Mehrzad Mahdavi about the explosive growth of AI and its impact on the financial services. Panelists: Jane Buchan, CEO, Martlet Asset Management; Nicolaus Henke, Senior Partner at McKinsey, Founder McKinsey Analytics, Chair QuantumBlack; William J. Kelly, CEO, CAIA Association; and Mehrzad Mahdavi, Executive Director, FDP Institute. |
Ethical Use of Machine Learning in Financial Markets – Myth or Miracle? Date: October 2, 2020 Our discussion will focus on the ethical use of AI released by financial services regulators can be operationalized to help industry professionals and executive teams alike think about opportunities, risks as well as required actions to strive ethically in our data-driven world. Industry experts have divergent views on our topic: Some say that machines will never behave ethically - even human experts fail to do so. Others suggest the only chance for financial markets to become more ethical are intelligent machines. Panelists: Dan Liebau, FDP, Founding Director, Lightbulb Capital; Michael Oliver Weinberg, Head of hedge Funds and Alternative Alpha, APG; and William J. Kelly, CEO, CAIA Association. Tags: FDP, Machine learning, AI, Ethics, Finance, Data, Data Science, CAIA Association. Panelists: Dan Liebau, FDP, Founding Director, Lightbulb Capital; Michael Oliver Weinberg, Head of Hedge Funds and Alternative Alpha, APG; and William J. Kelly, CEO, CAIA Association. Tags: FDP, Machine learning, AI, Ethics, Finance, Data, Data Science, CAIA |
Integrating Disruptive Innovation Into an Organization's DNA Date: September 9, 2020 Description: CAIA CEO Bill Kelly and Cathie Wood, Founder and CEO of ARK Investment Management, discus
“Innovation is the Key to Growth” – ARK Investment Panelists: Cathie Woods, CEO & Found Ark Investment and William J. Kelly, CEO, CAIA Association |
Eagle Alpha Discusses Alternative Data for Investment Strategies Date: September 2, 2020 Description: Ronan Crosson (data strategy) and Thomas Combes (data science) of Eagle Alpha will review what is Alt Data and share market trends and adoption. They will discuss ROI on alt data and show use cases for the most popular datasets for both discretionary funds and quants funds. While highlighting the importance of getting the processes right they will touch upon the end-to-end process: Discovery, Prioritization, Evaluation, Procurement & Integration. The session will also include a deep dive on quality testing for alternative datasets. Panelists: Ronan Crosson, Director, Data Strategy & Analytics, Eagle Alpha; Thomas Combes, Head of Data Science, Eagle Alpha and Keith Black, Ph.D, CAIA, CFA, FDP, Managing Director, Content Development, CAIA Association. |
Making Sense of Machine Learning Date: August 19, 2020 Description: Machine learning (ML) enables powerful algorithms to analyze financial data in new and exciting ways. But this excitement is often tempered by fear that investors don’t really understand why a model behaves the way it does. We need to move beyond this “black box” stigma. We propose a framework that demystifies the predictions from any ML algorithm. Our approach computes what we call a “fingerprint” for a given model’s linear, nonlinear, and interaction effects that drive its predictions — and ultimately its investment performance. In a real-world case study applied to currency return predictions, we find that popular ML models like neural network and random forest think in ways that do indeed make sense, and which we can begin to understand. These fingerprints empower investors to describe and probe the similarities and differences across ML models, and to extract genuine insight from machine-learned rules. Panelists: David Turkington, Senior Managing Director and Head of Portfolio and Risk Research, State Street Associates; Yimou Li, Assistant Vice President and Machine Learning Researcher, State Street Associates; and Aaron Filbeck, CFA, CAIA, CIPM, FDP, Director, Global Content Development, CAIA Association. |
Data Science in Production Date: August 6, 2020 Description: Nigel Noyes will reference architectures for using Data Science in production. Panelists: Nigel Noyes, Director, Automation, Data Science at Quicken Loans and Mehrzad Mahdavi, Executive Director, FDP Institute. |
Challenges of Algorithmic Fairness in Financial Services Date: July 29, 2020 As financial services sector increasingly adopts advanced algorithms, including machine learning and AI, there has been greater regulatory and public scrutiny on the potential for algorithms to replicate unfair bias and discrimination against disadvantaged groups, exacerbating existing inequalities. This webinar will walk through use cases in mortgage lending and in peer-to-peer lending to discuss the complex challenges of trying to make the algorithms "fair" in evaluating credit risk of minority groups. Panelists: Michelle Sengh Ah Lee, Ph. D., researcher Compliant & Accountable Systems Research Group, University of Cambridge, AI Ethics Lead, Deloitte UK and Keith Black, Ph.D, CAIA, CFA, FDP, Managing Director, Content Development, CAIA Association. Aaron Filbeck, CFA, CAIA, CIPM, FDP, Director, Global Content Development, CAIA Association. |
Factor and Asset Allocation: The Role of Networks and LASSO Date: July 16, 2020 Description: Dr. Gueorgui Konstantinov spoke about the financial Industry needs for new Methods to model and explain the complex market behavior. The industry is in a state of transition. The Asset Management Industry must avoid over-fitting, and adjust findings for false discoveries. Using machine learning and predictive models, investors can find asset and factor allocation solutions. Implementing LASSO regressions help to derive asset and factor allocation. Network theory and predictive models help to derive portfolio allocation in a new way, which successfully captures economic relationships. However, it is inevitable to evaluate the new strategies in a manner consistent with the requirements in the brave new financial world. Adjusting the Sharpe Ratios and t-Statistics become inevitable in the new set up. The focus in the webinar is in the application of new tools in Investment Management. Panelists: Gueorgui Konstantinov CAIA, FDP and Keith Black, Ph.D, CAIA, CFA, FDP, Managing Director, Content Development, CAIA Association. |
Machine Learning Prediction of Recessions: An Imbalanced Classification Approach Date: July 8, 2020 Description: We examine the problem of predicting recessions from a machine learning perspective. We employ a number of machine learning algorithms to predict the likelihood of recession in a given month using historical data from a set of macroeconomic time series predictors. We argue that, due to the low frequency of historical recessions, this problem is better dealt with an imbalanced classification approach. We apply measures to compensate for class imbalance and use various performance metrics to evaluate and compare models. With these measures in place, ensemble machine learning models predict recessions with high accuracy and great reliability. In particular, a Random Forest model achieves a near perfect True Positive Rate within the historical training sample, generalizes extremely well to a test period containing 2008-2009 financial crisis, and shows elevated recession probabilities during the last few months of 2019, associated with the tightened macroeconomic environment and worsened by global pandemic. Panelists: Al Yazdani, Chief Data Scientists & Founder, Calcolo Analytics, LLC and Mehrzad Mahdavi, Executive Director, FDP Institute. |
The Art and Science of Big Data in Quantitative Investing Date: May 21, 2020 Panelists: Elene Khoziaeva, CFA, Head of US Equity, Bridgeway Capital Management and Mehrzad Mahdavi, Executive Director, FDP Institute. Recording + Transcript |
Computational Drug Discovery Date: May 6, 2020 Description: The role of AI/ML and High-Performance Computing in Drug Discovery Panelists: Woody Sherman, CSO, Silicon Therapeutics & Adjunct Professor, UMass and Mehrzad Mahdavi, Executive Director, FDP Institute. |
Machine Learning Models in Credit Risk Analysis Date: April 29, 2020 Description: Mr. Arifi demonstrated ensemble models in DataRobot and showed why FDP is important. That is, knowing the models and model parameters are more important than knowing how to program in python. Panelists: Imir Arifi, Ph.D., Head of Methodologies & Models in the Americas, USB and Keith Black, Ph.D, CAIA, CFA, FDP, Managing Director, Content Development, CAIA Association. |
Data Supply Chain Management Date: April 7, 2020 Description: Data Supply Chain Management is the collection, organization, flow and streamlining of data – including any pre-processing and normalization steps - to make it usable, guided by domain knowledge, for the next downstream process. Typically, this next step involves analysis via traditional statistical or contemporary machine learning tools. The end goal of the exercise is to generate insights that can imply customer value, inform revenue or pricing metrics, optimize costs and help gain a competitive advantage in the marketplace. Panelists: Ganesh Mani, Adjunct Faculty, Carnegie Mellon; Mehrzad Mahdavi, Executive Director, FDP Institute. |
Quantitative ESG Investing Date: April 1, 2020 Description: ESG investing is an area of active interest for both the investment and academic communities. Despite the intense interest, there currently is no agreed upon definition of ESG investing, or how to best build investment portfolios that incorporate both return and sustainability dimensions. (Both are important for sustainability-minded investors.) In this article, the authors categorize the broad types of ESG investing currently in the market and introduce an ESG investment framework. This results in a portfolio that optimally combines the dual objectives of alpha and sustainability outperformance. TOPICS: Portfolio theory, portfolio construction, ESG investing Panelists: George Mussali, CFA, Managing Director & CIO Equity Investing, PanAgora; Mike Chen, Ph.D., Director Equity Investing, PanAgora; Aaron Filbeck, CFA, CAIA, CIPM, FDP, Director, Global Content Development, CAIA Association. |
Usage of Alternative Data and ML in Asset Classes Date: March 25th, 2020 Panelists: Michael Oliver Weinberg, Head of Hedge Funds and Alternative Alpha, APG; Peter Strikwerda, Global Head of Digital Innovation, APG; Aaron Filbeck, CFA, CAIA, CIPM, FDP, Director, Global Content Development, CAIA Association. Slide Deck |
Long Term Machine Learning Predictions for US Equity Date: March 5, 2020 Description: Tony Guida co-wrote and edited the book "Big Data and Machine Learning in Quantitative Investment", one of the required readings for the upcoming exam. This webinar is titled "Long Term Machine Learning Predictions for US equity" and is a user case study of Chapter 7 of the book which Tony co-wrote with Guillaume Coqueret. Panelists: Tony Guida, Executive Director - Senior Quant Research/PM at RAM Active Investments, Mehrzad Mahdavi, Executive Director, FDP Institute. |
A Machine Learning Approach to Risk Factors: A Case Study Using the Fama-French-Carhart Model Date: February 27, 2020 Panelists: Joe Simonian, Ph.D., CIO Autonomous Investment Technologies, LLC, Mehrzad Mahdavi, Ph.D., Executive Director, FDP Institute |
Analyzing Text to Detect Risk Date: February 19, 2020 Description: Dr. Seoyoung Kim is a Professor of Business Analytics at Santa Clara University and co-author of "Zero-Revelation RegTech: Detecting Risk through Linguistic Analysis of Corporate Emails and Newsl" Natural language processing is a fast-growing area of data science for the finance industry. Recent advances in financial technology (FinTech) have dramatically transformed the financial landscape with respect to the way we access, invest, and transfer financial capital. In this article, the authors explore a promising avenue for the use of natural-language processing in an effective yet non-invasive method by which to monitor the health and integrity of financial institutions and corporations in general by analyzing corporate emails and news. Panelists: Dr. Seoyoung Ki, Profesor of Business Analytics, Santa Clara University, Kathryn Wilkens, CAIA, Sr. Advisor FDP Institute, Mehrzad Mahdavi, Executive Director, FDP Institute. |
Big Data is a Big Deal Date: January 29, 2020 Description: Gene Getman is a Client Portfolio Manager for the 1798 Alternatives group, focused on Investor Relations for the Hedge Fund business. He is the Product Specialist for the 1798 Q Strategy and other innovative or capacity constrained alternative investment strategies based in New York. More importantly: Gene is the co-author of "Big Data is a Big Deal: An investor’s guide to the applications and challenges of alternative data" Panelists: Gene Getman, CAIA, Client Portfolio Manager - 1798 Alternatives Group · Lombard Odier Investment Managers, Kathryn Wilkens, CAIA, Sr. Advisor FDP Institute, Mehrzad Mahdavi, Executive Director, FDP Institute. |
Data Ethics in Machine Learning and Finance Date: January 22, 2020 Description: Our conversation with Guen Dondé, head of Research at the Institute of Business Ethics. Co-researcher of "IBE Ethics at Work" and "Implications of AI on Business Ethics". Thought provoking, engaging, and great learning overall! Panelists: Guen Dondé, Head of Research, Institute of Business Ethics (IBE), Kathryn Wilkens, CAIA, Sr. Advisor FDP Institute, Mehrzad Mahdavi, Executive Director, FDP Institute. |
Brought to you by: | 2021 Financial Data Professional Institute© |
