PinnedInData Science CollectivebyAmeen Siddiqui·Aug 26Lag Features: Teaching Your Model to Remember the PastArticle 6 of 10 in the series: Feature Engineering for Time Series ForecastingA response icon1A response icon1
PinnedInGoPenAIbyAmeen Siddiqui·Aug 4Decomposing Time Series: Separating Signal from NoiseArticle 3 of 10 in the series: Feature Engineering for Time Series ForecastingA response icon2A response icon2
PinnedInGoPenAIbyAmeen Siddiqui·Jun 9Tabularizing Time Series: The Foundation of ML-Based ForecastingMost ML tutorials treat time series as just another dataset. That assumption will silently destroy your model’s performance. Here’s the…A response icon1A response icon1
Ameen Siddiqui·Oct 6Datetime & Categorical Features: The Last Mile of Time Series Feature EngineeringPart 10 of 10 · Time Series, Engineered
Ameen Siddiqui·Sep 29Seasonality Features: Dummies, Fourier Terms & BeyondArticle 9 of 10 in the series: Feature Engineering for Time Series ForecastingA response icon1A response icon1
Ameen Siddiqui·Sep 22Trend Features: Making Tree-Based Models ExtrapolateArticle 8 of 10 in the series: Feature Engineering for Time Series ForecastingA response icon1A response icon1
Ameen Siddiqui·Sep 8Window Features: Rolling, Expanding & Exponential SmoothingArticle 7 of 10 in the series: Feature Engineering for Time Series Forecasting
InData Science CollectivebyAmeen Siddiqui·Aug 18Outlier Detection in Time Series: Rolling Stats, LOWESS & STLArticle 5 of 10 in the series: Feature Engineering for Time Series ForecastingA response icon2A response icon2
InGoPenAIbyAmeen Siddiqui·Aug 11Missing Data in Time Series: Beyond Simple ImputationArticle 4 of 10 in the series: Feature Engineering for Time Series ForecastingA response icon1A response icon1
InGoPenAIbyAmeen Siddiqui·Jul 20Why Time Series Breaks Your ML Pipeline (And How to Fix It)Three lines of sklearn code that work perfectly on tabular data will silently destroy a time series model. This article covers what breaks…A response icon1A response icon1