future - Services and Pricing

full flexible functionality via futureNOW - limitations for futureEXPERT are indicated where applicable

to enable usage for forecasting or other analyses

• Handling of raw data in csv or tsv format with UTF-8 encoding, via futureEXPERT: additionally pandas dataframe.
• Possibility to define value and grouping variables/columns as well as a date variable/column. (At least one value and exactly one date column must be defined, grouping and additional value columns are optional.)
• Support of numeric date formats, e.g., YYYY-MM-DD, DD.MM.YYYY hh:mm:ss.

different from those in the raw data

by specifying rows and columns to delete

• Checking data plausibility concerning defined data types, missing values, and set thresholds.
• User-defined response to plausibility violations per column and type (e.g., deletion or setting replacement values). Convenient configuration only in the frontend, with the downloaded configuration file allowing seamless continuation in the Python client.

for time series creation, based on grouping variables (forecast level)

Half-hourly, hourly, daily, weekly, monthly, quarterly, or annual

For all time series (optional). Only data between start and end dates (inclusive) will be used for time series preparation.

based on grouping variables

by combining two existing value columns (summation, difference, or multiplication)

Option to select how to handle missing values in the target granularity in the aggregation - treat as missing or 0.

For re-use of the settings in the Python client or at a later point in time

displayed in interactive plots via futureNOW

Point forecasts and optionally prediction intervals up to max. 30 days or 12 months after the last available data point.

Up to five rolling forecasts based on an appropriate historical period of the available time series

• Option to use own factors on a daily or monthly basis.
• Option to use factors from POOL (see below).
• Manual selection of different lags per factor (up to 30 days or 12 months into the future or past).

of time series data, influencing factors, backtesting, and forecast results with download option

in tabular csv format

appropriate to the time series - see limitations for details

Support of time series at 7 granularities - half-hourly, hourly, daily, weekly, monthly, quarterly, annually

(also sometimes referred to as influencing factors, covariates or indicators)

• Manual definition of lags per covariate and time series or use of MATCHER results for lag selection, with manual adjustment options.
• Exponential smoothing as forecast method for covariates
• All covariates in a joint model

• Option to choose an additional method for incorporating factors into the forecast model.
• Choice of whether factors should be considered individually (single) or jointly (joint) in the forecast model.

Use of factors from POOL for forecasting

• Default: typical season lengths for the given granularity are checked.
• Alternatively, specific season lengths (including multiples) can be specified for checks.
• A fixed season length can also be set, by passing the season detection..

for the forecast object and historical factor data by interpolation

• Level shifts
• Significant structure changes in the occurrence of very small values or zero values

If desired, detection of quantized values in the data history (e.g., due to specific customer ordering behavior or packaging sizes) can be enabled for forecasting.

Calculation of rolling historical forecasts for all suitable forecasting methods, aligned with the set forecast horizon, with preset values suited to the time series (length, granularity). Options include:

• Defining the number of iterations
• Shift length
• Refitting on each iteration (significant impact on runtime)

• Preselection based on preprocessing-identified time series characteristics
• Final ranking based on backtesting results
• Option to set one accuracy measure for each of the two time series groups (smooth/erratic and sporadic/lumpy), which is used as ranking and selection criteria.
• Forecast steps with weighting (step_weights) for ranking can be set.

For each successfully optimized forecasting model with complete backtesting results, additional accuracy measures can be calculated.

Forecast results of all models with a full backtesting result are checked for plausibility.

If no model passes all iterations and plausibility checks, fallback logic with a few appropriate methods for the time series ensures a forecast is provided.

• Time series with up to one covariate
• Forecasts including data history, possibly with prediction interval (per successful model) and certain preprocessing results
• Backtesting forecasts (one plot per model and iteration)

• Overview of certain preprocessing results and information about the best model per time series (as data frame)
• Forecasts, possibly with prediction intervals, per best model and time series (as data frame)

Ranking and selection of factors for a forecast object by examining predictive power and comparison with a benchmark model

from a given set (by specifying minimum and maximum lag or a list of lags)

relating to publication delay and the time offset between forecast object and factors:

• Option to exclude covariates with no temporal lead relative to the last data point of the forecast object (and thus unsuitable for any forecast step).
• Option to set the maximum allowable time difference between the most recent value of the influencing factor and the forecast object.

Support of time series at 7 granularities - half-hourly, hourly, daily, weekly, monthly, quarterly, annually

• Ranking of successful factors with best lag per forecast object including benchmark model.
• Time series values of forecast objects.
• Data history of ranked covariates.

Plot of the time series with a covariate shifted in time (by the set/identified lag)

for use in other modules. Examples include:

• Various daily weather data at selected german weather stations
• Holiday & workday information
• Selected economic indicators

Regular updates for available factors (intervals depend on granularity)

Overview of available factors with relevant metadata (e.g., region) in table form, including text search and filters

Provision of latest and historical data snapshots

Support requests are prioritized. The request must be sent from the e-mail address used for registration.

• Working days as in Würzburg, Bavaria (Germany)
• Indicated times are based on the current time in Berlin, Germany

within the service times