Archive for January 2018

Practical Time Series Forecasting – Know When to Roll ‘em

By KDD | January 29, 2018

times series forecasting rolling holdout samples

“Prediction is very difficult, especially if it’s about the future.” ― Niels Bohr, physicist Holdout samples are a key component to estimating a “useful” forecasting model. Set aside data at least equal in length to your forecast horizon (“holdout sample”). Build your models on the remaining data (“modeling sample”). And compare the candidate models’ forecast…

Practical Time Series Forecasting – To Difference or Not to Difference

By KDD | January 22, 2018

time series forecasting stationarity differencing

“It is sometimes very difficult to decide whether trend is best modeled as deterministic or stochastic, and the decision is an important part of the science – and art – of building forecasting models.” ― Diebold, Elements of Forecasting, 1998 A time series can have a very strong trend. Visually, we often can see it. Gross…

Practical Time Series Forecasting – What Makes a Model Useful?

By KDD | January 15, 2018

“In God we trust. All others must bring data.” ― W. Edwards Deming, statistician So, you have estimated a bunch of forecasting models and realize (kudos to you!) that they are “all wrong” (ala George Box). But your forecasting deadline is looming, and you need to find some useful models on which to base a…

Practical Time Series Forecasting – Know When to Hold ‘em

By KDD | January 8, 2018

times series forecasting holdout samples

“The only relevant test of the validity of a hypothesis is comparison of prediction with experience.” ― Milton Friedman, economist Holdout samples are a mainstay of predictive analytics. Set aside a portion of your data (say, 30%). Build your candidate models. Then “internally validate” your models using the holdout sample. More sophisticated methods like cross…

Practical Time Series Forecasting – Data Science Taxonomy

By KDD | January 2, 2018

times series forecasting machine learning

“Big data is not about the data.*” ― Gary King, Harvard University (*It’s about the analytics.) Machine Learning. Deep Learning. Data Science. Artificial Intelligence. Big Data. Not a day goes by that one or all of these buzzwords stream past in our business news feeds. Data analytics has become mainstream. And you better jump on…