Forecasting and Reporting with Cognos TM1 and SPSS

Cognos TM1 Implemented forecasting and reporting systems have had many benefits to businesses.

These benefits might include (by are not limited to):

1. Improved consistency – a single source for forecasting and reporting.
2.  Decreased overall “processing time” for reporting forecast and actual information.
3.  Decreased manual intervention – fewer “touch points”.
4.  Provide the ability to easily make “quick updates” and resubmissions.
5.  Increased robustness of both forecasting and reporting process; reduced errors.
6.  Ability to “automatically” see consolidated forecasts data – in local currencies!
7.  Increased access to detail levels of a forecast.
8.  Enhanced analysis ability for the field, improved performance and access to data for remote users.
9.  “OLAP engine” availability to the branches.
10.  In memory- automatic currency conversions – “on the fly”.
11.   Ability to consolidate on multiple system accounts, function codes, etc.

NBT

The Future of Big Data

With some guidance, you can craft a data platform that is right for your organization’s needs and gets the most return from your data capital.

Get the Guide

So what is the next big thing?

If we consider that many forecasts are based upon “time series observations” such as weekly market share percentages, daily inventory levels or actual sales dollars, we can then look to leverage a tool such as IBM SPSS.

IBM SPSS Statistics provides us with a “comprehensive system” for analyzing time series data and the Forecasting optional add-on module provides the additional analytic techniques to actually create a continually learning time based predictive forecasting model.

 Building Models and Producing Forecasts

The IBM SPSS Forecasting add-on module provides two procedures for accomplishing the tasks of creating models and producing forecasts.

• The Time Series Modeler procedure creates models for time series, and produces forecasts. It includes an Expert Modeler that automatically determines the best model for each of your time series. For experienced analysts who desire a greater degree of control, it also provides tools for custom model building.
• The Apply Time Series Models procedure applies existing time series models—created by the Time Series Modeler—to and active dataset. This allows you to obtain forecasts for which new or revised data are available, without rebuilding your models. If there’s reason to think that a model has changed, it can be rebuilt using the Time Series Modeler.

Other Features

SPSS also provides numerous other features that can help in building a forecast. For example, based upon experience, data available may not always arrive as complete as it could be from source systems and EDW’s. In order to make your data as valuable as it should be, you can use SPSS to review and “transform” it. A number of data transformation procedures are provided in SPSS and can be useful in time series data analysis.

• The Define Dates procedure generates date variables used to establish periodicity and to distinguish between historical, validation, and forecasting periods.
• The Create Time Series procedure creates new time series variables as functions of existing time series variables. It includes functions that use neighboring observations for smoothing, averaging, and differencing.
• The Replace Missing Values procedure replaces system- and user-missing values with estimates based on one of several methods.

Conclusion 

While an experienced eye may still be needed to produce an accurate forecast, why not automate the process with SPSS and use your team’s time more productively – by reviewing and adjusting?