I tried the third option and used PMI ( purchasing managers' index) which is a leading economic indicator as additional regressor. Use External Drivers (Even Better Solution): use additional external data or economic indicator as regressor.Event Forecasting (Better Solution): leverage on holiday or event effect, this is tricky as the policies and lockdown periods are different from countries to countries, from months to months.Flag Outliers (Simple Solution): simply flag the outliers and remove/replace them which is equivalent to throwing out the data.This article on how to forecast demand despite COVID on Medium summarise three options and here I shared their equivalent fixes for fbprophet: I am using fbprophet for a monthly sales prediction problem (5 years of historical data with 12 months ahead prediction) and have been researching on options on how to deal with covid-19 shock. Thank you again for making this amazing tool. Notice my extra-regressor here plays negative instead which is not expected.Ī quick comparison with true-value, predict-values.ĭo you think this is purely luck? And any idea of what might be going on here to make this lucky improvement happen? Then, boom, it actually performs better in predicting the Feb and March data (after adding Jan-2020 data to train):Īlso notice here my extra regressor's impact is positive which is expected. M5.add_seasonality(name='monthly-post-corona', M5.add_seasonality(name='monthly-pre-corona', I have models in R thus here is the code of what I did. Step4: Lag the calculated mean by 1 or 2 weeks (depends on the use case). Step3: Calculate a rolling mean of 2 or 3 or 4 weeks (depends on the use case).Thus, since I couldnt change coefficients, I introduced moving average into my linear regression models (an idea borrowed from Time Series), what this means is that I am adjusting my intercept after fitting my model. The challenge I had was that training another set models for covid would mean going back to model risk and agree on the coefficients(price elasticities) and the impacts it will have also not to forget feature selection. I am using log-log linear regression model to estimate price elasticities ( didnt use ARIMAX as that might reduce the price elasticity effect) of customers and then predict into the future, since the covid period my models deteriorated considerably. Now this isn't using Prophet but simple linear regression but I believe this can be extended. I want to throw an idea into this mix, which I have implemented in linear regression models I maintain at work.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |