STEM models service demand and equipment installation, categorised by user, service and geotype, and enables decision-making based on quantitative results. The process of creating a model already provides significant insights, but far more value is realised through the processing and comparison of results of a wide range of input scenarios and sensitivities.
STEM is a flexible analytical system which adds user-definable inputs and formulae, multi-dimensional scenario management and sensitivity analysis to the STEM business-modelling software for networks.
The use of mathematical expressions to link user-defined inputs and to define selected transformation outputs allows topic-specific model parameters to be added to individual model elements.
The concepts of dimensions and variants are used to generate orthogonal sets of scenario results. This flexible construct has a wide range of applications, including the comparison of network profitability results arising from varying technology choices and roll-out plans
A related sensitivity concept is used to generate delta result sets and tornado charts by varying selected inputs in turn in order to perform general risk and sensitivity analysis.
Creating scenarios is easy in STEM
Suppose you want to capture several different economic futures within a model, for example, to explore the performance of different technology solutions, or to compare a colleague's demand forecast with your own. A vastly simplified cellular model illustrates these basic techniques relating to busy-hour bandwidth requirements for 3G capacity across a number of base-station sites in a green-field network roll-out. In our base scenario, with roll-out over 300 sites over two years, increasing demand for higher bandwidth services quickly exceeds basic coverage capacity with standard carriers offering 2.5Mbit/s bandwidth.
Busy-hour bandwidth, and deployment of carriers
First we add an alternative technology solution which offers twice the bandwidth capacity in the basic carrier, at a higher unit cost but lower cost per Mbit/s.
Create scenarios for related inputs, and enter alternative values
The Unit Capacity for Enhanced is changed to 5.0 Mbit/s to reflect the higher capacity, and the Capital Cost is set to the higher cost of EUR125 000. The two scenarios can immediately be run and the results compared, as follows:
Enhanced technology may reduce deployment and long-term capex
So far we have created scenarios for two related inputs which vary coherently through association with the same 'Technology' dimension. Now we compare two different demand forecasts by choosing a new dimension when creating scenarios for the service penetration and nominal bandwidth per connection inputs. We rename this dimension as 'Demand', with variants 'My forecast' and 'Alternative forecast', and then enter alternative demand data in a separate variant data table.
This approach allows these demand parameters to be varied independently of the technology, resulting in four distinct but consistent scenarios which can be examined in parallel. The Enhanced technology pays off in the long term with the Alternative forecast, but not with the original demand parameters.
Two-dimensional scenario space
Comparative business results
Exploring sensitivities to avoid the ‘rubbish in, rubbish out’ effect
A business model is only ever as good as the assumptions behind it, and when there are very many inputs, it can be hard to know which of these merits the most careful research. Therefore a key part of the modelling process is to perform sensitivity analysis, i.e. to determine the relative impact of various model assumptions on the main outputs.
Sensitivity elements automatically generate consistent results sets for a model ('deltas') where one or more parameters are perturbed by plus or minus a number of percentage points (or absolute steps, or steps between explicit minimum and maximum values).
The STEM Editor allows you to create multiple, overlapping sensitivity sets, and to choose which should be run with the existing selection of scenarios to run. The Results program automatically selects the appropriate delta results sets for graphs when you ask to graph a given sensitivity - you don't have to worry about how many steps are generated.
Sensitivity analysis results as time series
A parameter Label input can be used to group linked parameters (as well as to provide a more concise label for the chart), so that they will be perturbed together in order to generate correlated sensitivities for those inputs. This makes measuring the sensitivity of the results to across-the-board tariff movements for three services much simpler than re-structuring the model to drive all three tariffs from a common uplift driver.
Tornado chart for sensitivity analysis
In addition to the simple charting of comparative time-series results, i.e. all delta results sets shown on one graph as shown above, options are also provided to create so-called tornado charts which highlight the relative sensitivity of separate, independent inputs.
Illuminating strategy through business modelling
User-defined inputs and transformation outputs preserve the object-based approach which is fundamental to the system-generation of calculation structure which increases productivity and ensures clarity and reliability.
The integrated multi-dimensional scenario manager provides effortless agility in the exploration of new scenarios, enabling new insights which are often too time-consuming to explore in a spreadsheet, and guarantees a consistency of analysis throughout.
Native sensitivities are the fastest way to test the robustness of a model to uncertainty in assumptions and future market conditions.
