This post is also available in: Spanish
The three main types of analysis in an iBPMS like AuraPortal are:
- Descriptive Analytics, (Dashboard, Reports, Consultations)
- Predictive Analytics (Simulation, Data Mining, Prediction, Patterns)
- Prescriptive Analytics (Optimization)
Descriptive Analytics uses data consultation techniques to give information on what has happened, thus answers “What happened?” style questions.
It is a type of analytics which describes a phenomenon for study. It is the preparatory stage of investigation which organizes the results of characteristic observations, the factors involved and other variables.
Descriptive research seeks to specify properties, characteristics and important features of any phenomenon that needs to be analyzed”
(Hernández, Fernández and Baptista)
Predictive Analytics uses statistical models and mathematical prognostic techniques to understand the future and thus
answers “What could happen?” style questions, for example:
- Given a historical sequence of product sales, how much can I expect to sell of this product in the next 15 days?
- Given a customer base with their purchasing history, can I calculate the characteristics which are relevant for clients in order to predict what items will interest them?
- Based on data history of repairs I’ve had to make on my machines, can I find relations that help me predict the breakdowns that will happen in the short term?
- Based on the history of non-payments in my customer base, can I infer characteristics that will help me identify which ones, even if they haven’t defaulted, are more likely to do so?
This type of analytics can compare and describe two phenomenons. This process is more complicated than descriptive analysis which basically consists of establishing a comparison of variables between groups of study and control groups without applying or manipulating these variables. However it refers to the proposal of hypothesis that the researcher seeks to prove or disprove.
Prescriptive Analytics uses optimization algorithms to give the best assessment of possible results, thus answers “What should we do?” style questions, for example:
- A client’s propensity to buy certain items can be used to calculate what campaigns it is best to launch for this client.
- It is interesting to predict the breakdowns that will take place in my machines to conduct preventive maintenance at the best time.
- A client’s propensity to default is important when considering whether to give them credit.
It provides information like which product is best to sell in a certain country, which would be the best option to keep a customer, what should be done to optimize the production and inventory of the supply chain, etc.
These three types of analysis form Intelligent Analytics which helps entities:
- To determine the inventory level of a product or part
- To offer special incentives to ensure customer loyalty
- To identify best selling products and to see if this is the case in all distribution channels
- To assess scores so that executives can quickly detect operational exceptions
- To identify customers who are reducing their purchases (KPI)