Harvard Data Science Review

Happy to share that our article “Data Science for Central Banks and Supervisors: How to Make It Work, Actually”?(joint with Patty Duijm) has been accepted for the Harvard Data Science Review and is available at https://lnkd.in/e995xyGp or below. Many thanks to the #DNB_Data_Science_Hub team for being amazing and delivering such inspiring results.

22/11 @8:30 am Join us for a conversation with?Xiao-Li Meng?on Learning, Teaching, and Communication in the Age of AI: Wisdoms and Warnings from?Harvard Data Science Review where he will share his reflections?on?how the science of artificial intelligence depends on human intelligence and diligence,?based on his teaching, research, and mostly?his editorial experience?from HDSR, which features?everything data science and data science for everyone.?In particular,?through Stepping Stones and the column on Minding the Future, HDSR examines educational policies and innovations that improve data science education at all levels, from early childhood to the corporate boardroom. The conversation will be moderated by?Manuel Fernández, Innovation Editor, El Mercurio Newspaper. About the speaker Xiao-Li Meng,?Whipple V. N. Jones Professor of Statistics, former Dean?of the Graduate School of?Arts and Sciences (GSAS)?and founding editor-in-chief of?Harvard Data Science Review?(HDSR) The presentation will be with simultaneous translation. Limited spaces. RSVP by November 18,?email:?[email protected]. Address: Dag Hammarskjold 3269 Vitacura, first floor Presented in collaboration with Harvard Data Science Review, Harvard Club de Chile, Fundación Luksic, and REimagina Fundación

????”The future of #AI in various applications is centaur!” ?????? In this paper at Harvard Data Science Review, we discuss a paradigm shift towards centaur-based AI methods and answer some fundamental questions regarding this important shift. Public Impact Analytics Science Lab (PIAS-Lab) at Harvard Harvard Data Science Initiative Mossavar-Rahmani Center for Business and Government at the Harvard Kennedy School Harvard Kennedy School

The Harvard Data Science Initiative has launched a Rock Band! You can follow them on Instagram (@project42.HDSI). Importantly, they will perform as a part of the Festival of Italian Creativity this Thursday, November 21, around 7 pm at the Federal Reserve building (600 Atlantic Avenue in Boston. Please note you must register for the event at https://italyinboston.org/ and is free.? We will see you there! Harvard T.H. Chan School of Public Health

We are hiring a Senior Coordinator for Engagement and Events, whose role will focus on communication, outreach, and event coordination efforts. Come work with us! https://lnkd.in/eudaUM3m

Our latest issue (6.4, Fall 2024) is out and filled with lots of great content covering a wide range of topics including: the #2024Elections, #Causalinference, #DataScienceEducation, #AIandCreativity and #ReproducibleResearchStandards. Read the issue now starting with the insightful editorial by Editor-in-Chief Xiao-Li MENG Harvard Data Science Initiative The MIT Press https://lnkd.in/esuYPNhN

A wonderful and insightful article by Stephen Stigler on "Some Early History of Data Security" in Harvard Data Science Review: > https://lnkd.in/eGnyDH5Y #Data #Security #DataSecurity #Lottery #Gambling #History #Stigler #HDSR

Harvard Data Science Review just published our work on creating a real-time Election Night model. The model takes our fast and accurate county level election results and turns it into a live probabilistic assessment of who will win a race as new votes come in. Be sure to check out this model live in action on The Hill and NewsNation this Tuesday. https://lnkd.in/e-8DBz-q

Gratified to see some of my research published today... and just in time for the election in Harvard Data Science Review Abstract: "We evaluate the predictive power of the leading explanatory models of turnout in the academic literature. We compare the power of using registration, lagged vote, demographics, electoral competition, and early vote data to predict turnout. We specify models to capture each of these approaches to understanding turnout, fit those models to the relevant data from prior elections, and use the estimated parameters from prior years and the relevant observable data from the day of the election in the current year to predict that year’s election. The simplest and most naive model, the Registration Model, outperformed other models in predicting 2016 turnout using 2012 election data and 2020 turnout using 2016 election data. These findings are consistent with classic understandings of which factors most drive turnout, and demonstrate that in modern elections the propensity of registered voters to turn out in presidential elections is fairly stable. Saturated models that combine many of these predictors are common in the academic literature that attempts to explain levels of turnout. We find that such saturated models overfit the data and lead to less accurate predictions than parsimonious models."

?? Our Fall issue is out (6.4) is out and it contains a special theme on the 2024 U.S. presidential election. Edited by Liberty Vittert Capito, Ryan Enos, and Stephen Ansolabehere, the six special themed articles collectively provide an academic and industry look at multiple aspects of the election including predictions on who is going to win on November 5. #2024PresidentialRace #ElectionPolls #Election2024 #Voting #ElectionForecast The MIT Press https://lnkd.in/eD-2MGux