you can find all the details about how to create and use events in FS in chapter 12 of the following doc https://support.sas.com/documentation/onlinedoc/forecast/14.2/fsug.pdf   thanks alex ... View more

maybe you can try 1st predicting if the target is 0 or not (a classification model), and then 2nd predicting the target if the they are not 0. You need to exclude the 0 observations from the 2nd model. alex ... View more

you can try adjusting the series y_t by (number of days in an average month)/(number of days in month t). Forecast using the adjusted series as usual, and then adjust the forecast back. You will need to prepare the adjustment factors into the future as well. If you are using Forecast Studio, you can create the adjustment factor as a variable and use it in a project to pre and post adjust the series and forecasts. alex ... View more

Hi Jade, Forecast Studio supports utilizing the validation and test data set to evaluate the model performance. You can set HOLDOUT (number of periods) or HOLDOUT_PCT (percent of total periods) to use validation data set to diagnose and select models. You can use BACK (number of periods) to use test data set to evaluate true model performance as the test data is not used in any way during the modeling process. In data mining world, the training data is partitioned randomly (or in a fashion that is not time related) to form the training, validation, and test data. Models will be built based on the training data and guarded by the validation data. That's the end of modeling process. However, in forecasting, the data has to be partitioned by time sequences since you are not building a model to forecast any random period in the past. The model is built to forecast into the future periods in sequence. The test data has to be the most recent observations, and then the validation data, and then the training data. You might lose the recency effect (most recent data are typically important for forecasting) if you are holdout out data for validation purpose (or the test data). In Forecast Studio, the validation data set (via the HOLDOUT option) will be used for diagnose to create model candidate list. Then the training + validation data will be used to select the best model from the model candidate list, and generate forecasts. This is the most common practice. However, If the data has long enough of history, you do have the luxury to compare models with the test data (via the BACK option). But i would use the BACK for reporting the expected model performance, and then set the BACK to 0 and generate forecasts using the selected model in order to utilize the latest data. sorry for the long reply... have a nice weekend alex  ... View more

There are several ways to model an "ANN" model.   1. Using neural net alone to model ANN(p,k) (i think it should be p, not q). You have to create p lags of the dependent variable as the input to the neural net with k hidden neurons. In addition, you can diff the data first and then modeling the diff instead of the original series so you are modeling something like ANN(p,d,k)   2. Stacking models. Take the residuals from the ANN model from 1 and modeling them using ARIMA(p,d,q). The final forecast will be the ANN forecast + ARIMA forecast   3. Ensemble models. Model ANN and ARIMA separately and take some sort of averaging (e.g. straight up average or regression based averaging) of the forecasts   4. Recurrent neural net. This model is much more complex and takes a lot of time to train. In practice methods 1 to 3 should be more than sufficient. thanks Alex ... View more