Forecaster Explainability Results Clarification

Question

We transitioned from PlanIQ to Forecaster and started importing explainability results into the model. But I’m struggling to interpret some of the since there is no information in Anapedia.

Here are examples from the sales explainability results list:

Historical: trend (ETS, ENSEMBLE)

Historical: linear_trend (ENSEMBLE, PROPHET, MVLR)

Historical: exponential_downwards_trend (MVLR, ENSEMBLE)

Historical: exponential_upwards_trend (MVLR, ENSEMBLE)

Historical: Auto Regressive 1(SARIMAX, ENSEMBLE)

Historical: Auto Regressive 2 (SARIMAX, ENSEMBLE)

Historical: Auto Regressive 3 (SARIMAX, ENSEMBLE)

Historical: Seasonal Auto Regressive 24 (SARIMAX, ENSEMBLE)

Historical: Seasonality_Yearly (MVLR, ENSEMBLE, PROPHET, ETS)

Related: Z__related_data_column lagged 1 month (MVLR, SARIMAX, ENSEMBLE, PROPHET)

Related: related_data_column_4  (MVLR, SARIMAX, ENSEMBLE, PROPHET, TIMESFM)

dayofweek (LIGHTGBM)

dayofmonth (LIGHTGBM)

dayofyear (LIGHTGBM)

distance_from_ts_start (DEEP AR)

metadata_2_g1_list__code__0 (LIGHTGBM)

Here are my questions:

1. Why are multiple trend types generated (linear, exponential up/down, etc.)?

If exponential_downwards_trend = -0.22 and exponential_upwards_trend = 0.22 for the same item, how should I interpret that? Do they cancel each other?

2. What is the difference between Historical: Auto Regressive 1, Historical: Auto Regressive 2, Historical: Auto Regressive 3, and Historical: Seasonal Auto Regressive 24?

Is Auto Regressive capturing short-term lag memory while Seasonal AR captures longer cycles?

3. I see metadata fields being used in LIGHTGBM.

Anapedia mentions metadata usage for DeepAR. Is metadata also used as categorical features in LightGBM?

4. How does a list item code have an effect in the result? Are they encoded categorically, or could they be interpreted numerically?

Any clarification or official documentation would be helpful.

Seyma Tas

NatalieC · Answer

Hi Seyma, Our support team has reached out directly to address these questions, but sharing here the response:

Please note that Ensemble simultaneously runs ETS, SARIMAX, MVLR and Prophet, so those features could appear in Ensemble explainability results.

Question #1: More information is available on this page . Because the reported values represent feature contribution, there could be both negative and positive exponential trend over the duration of the forecast horizon.

Question #2: Yes. Multiple historical and seasonal autoregressive features are generated for the SARIMAX algorithm and those that are significant to the forecast are included in the explainability results.

Question #3: LightGBM uses internally generated metadata derived from the Historical and Related Data, not the Attributes module line items. This is an area of additional research and development.

Question #4: List item code must be unique and does not affect the result. Categorical data that does not change over time can be included in the Attributes module.

unknown · Answer

This content has been removed.