Thomas OriolinDatapredCovid-19 and raw materials — The many shapes of instabilityThe Covid-19 crisis is having a violent impact on energy and raw material markets. But the traditional concept of price volatility doesn’t…Dec 11, 2020Dec 11, 2020
Thomas OriolinDatapredDirect Material Procurement: Beating The Market Is Not The PointDatapred’s machine learning software for direct material procurement helps companies save 3–5% off their commodity, energy and raw…Nov 5, 2019Nov 5, 2019
Thomas OriolinDatapredThe Next Big Thing (In Business Intelligence)It’s always fun to watch business consultants and IT companies search for the next buzzword — throwing candidates to the wall, hoping that…Sep 26, 2019Sep 26, 2019
Thomas OriolinDatapredWhat Is Time Series, And Why Is It Special?Our definition of times series is: sequentially revealed, time-stamped and time-critical data.Aug 22, 2019Aug 22, 2019
Thomas OriolinDatapredStop Stacking, Start AggregatingData scientists are waking up to the fact that combining multiple, relatively simple predictive models is often more efficient, when…Aug 6, 2019Aug 6, 2019
Thomas OriolinDatapredProductizing Machine Learning Models — What Is Required?We talk a lot with the data science teams of industrial companies, and it is striking how unaware they usually are of the gap between a…Jul 3, 2019Jul 3, 2019
Thomas OriolinDatapredCustom Loss Functions — What They Are And Why You Need ThemMachine learning models often disappoint in production for a simple reason — they have the wrong target.May 28, 2019May 28, 2019
Thomas OriolinDatapredBest Practices For Bulletproof Time Series ModelingOur goal in this post is to discuss our standard strategy (beyond respecting basic time series modeling principles) for building accurate…May 13, 2019May 13, 2019
Thomas OriolinDatapredThe Problem With Deep Learning And Time SeriesIndustry is finally waking up to the potential of machine learning for predictive analysis. But data scientists faced with a prediction…Apr 8, 2019Apr 8, 2019
Thomas OriolinDatapredHow Should You Handle Seasonality?Seasonality — recurring but not necessarily periodic data patterns — is a staple of time series modeling. Since capturing true seasonality…Mar 22, 2019Mar 22, 2019
