Forecasting Strategy
Following up on the revolution in weather forecasting: How Machine Learning might replace traditional weather models
Remember our article about new models by Google outperforming traditional weather models? Progress has been made since then: meet “Aardvark Weather,” a cutting-edge system built on machine learning (ML) that’s transforming how we predict the weather—potentially for...
Chatbots Beating Human Forecasters in Election Predictions
“No traditional poll will exist by the time the next general election occurs” – that’s a bold prediction by AI forecasting startup Aaru’s founder Cam Fink. The startup wants to revolutionize forecasting in every application of business- and everyday life. For now they...
Lichtman predicts Kamela Harris to win—will his “13-Keys to the Whitehouse” be wrong in 2024?
All large U.S. newspapers are coming out with opinion polls that try to give us a snapshot of who the U.S. electorate would vote for if the election were held today. Statisticians such as Nate Silver have tried to make election forecasts more accurate than individual...
Predicting Extraterrestrial Threats using AI
As on earth, there are also storms in space. While storms on earth are tangible, space storms are less evident as they consist of charged particles. The effects of these storms can be pleasant – geomagnetic storms are responsible for the northern lights – but can also...
Machine Learning in Retail Forecasting – Results from the M5 Competition
Accurately predicting sales data is a challenge all retail companies face. Especially in light of the vast availability of data and solutions to evaluate data, firms at the cutting-edge of forecasting technology can gain an invaluable competitive advantage. The...
Machine Learning Beats Statistical Models in Weather Forecasting
Especially in light of climate change, modelling medium-range (next 10 days) weather is becoming increasingly important. The current industry gold-standard is the High Resolution Forecast (HRES), produced by the European Centre for Medium-Range Weather Forecasts...
Blockchain Prediction Markets
Prediction markets and betting on a person’s believes about the future is not a phenomenon linked to the rise of the internet, but an activity dating back hundreds of years. The first confirmed accounts of such activities date back to 1503 when Italian merchants...
Forecasting the next 100 years
The Metacalculus prediting platform has published a very useful report, using both a group of superforecasters and a large group of forecasters, to make forecasts about key trends for the next 100 years. You download full report here.
Are icevs or bevs more modular? Implications for the future of the auto industry
By Johann Peter Murmann and Benedikt Schuler How will the technological shift from internal combustion engine vehicles (ICEVs) to battery electric vehicles (BEVs) change the architecture of the automotive industry? To explore this question, we systematically compare...
Gigerenzer on Strength and Weakness of AI
Gerd Gigerenzer has written a wonderful new book How to Stay Smart in a Smart World: Why Human Intelligence Still Beats Algorithms.| It strikes me as an update of Dreyfus and Dreyfus 1992 book "What Computers still can't do." Below is a video with Gigerenzer on...
Gerd Gigerenzer on “Risk Literacy”
This is a very useful talk based on Gigerenzer's book. Using the example weather forecasts he makes he explains that many people do know know why the relevant reference class is when we are told it rains with 30% proability. He also councils that we always need to...
“Predicting Future is Possible” Very informative Phil Tetlock interview in NY Times
Even for someone who is somewhat familiar with Tetlock's ideas on forecasting skills, this podcast is very informative. You can listen to it or read the transcript at the NY Times.