2020 election Swing State Series - Michigan Votes win elections, not polls. And you can’t vote if you don’t register. Last October, I built a voter model (CE-VM) and showed how registrations in Michigan were trending in favor of the President. Elevated registrations are actually occurring in 2016 Republican counties, a phenomenon being
china 2020 Outlook Entering year 4 of a 15-year private sector confidence cycle, expect a mixed bag for risk-on asset classes in a world weighed down by the continued miscalculations of public sector actors. Major Themes: A Mixed Bag for Risk-on Assets in 2020: The S&P 500 rises modestly; so does
2019 2019 Year in Review Entering 2019, I wrote here about three themes impacting markets, politics, and society. Each has materialized, in some form, and with varying impact. Tangible Government Regulation of Big Tech PlatformsDramatic and Rapid Breakdown Of Post-WW2 Multilateral StructuresMilitary Conflict Between India and Pakistan and Between Israel and Arab States I also
machine learning Trump Can Hold The Rust Belt (Part 1: Michigan) Conventional wisdom and polling are that Democrats can regain the Rust Belt firewall in 2020 (Wisconsin, Michigan, Pennsylvania). I built a Random Forest model called CE-VM to predict likely 2020 total votes (turnout) in every U.S. county. CE-VM predicts that~135M votes will be cast in 2020, up from
deep learning Believe Me When I Say To You, I Hope You Love a Trade War Too! NLP Analysis of the President’s Tweets on Trade (With Some Inspiration From Russians by Sting) In Europe and America, There’s a growing feeling of hysteria. Markets are catching up to the staying power of the trade war. As I wrote on May 23rd here: Investors continue to
