A.I Insight
An exciting exploration into the possibilities of your data and how A.I can help your strategic goals. The page i split into two sections
-
Predictive Analytics - This is a 'lite' version of the full page available in the 'Enterprise' version. It allows prediction forward of up to 12 months of data using various forecasting models. These models will provide data to assist
-
Anomaly detection - Using A.I detection methods, the algorithms provide the ability to present data outliers and help a user understand why performance is lacking in departments, locations and customers
Geomaping
A visual mapping tool to enable an overview of a geographical region and how it is performing. Mapping pins provide a colour coded representation of the performance with the ability to drill to lower locations. Full capability to analyse exactly what/why region/city/custom location is underperforming.
Predictive Analytics
Predictive analytics provides advanced A.I analytical tools to maximise and fulfil your data to it’s full potential. A variety of tools offer data forecasting including:
​
What If? Analytics – What-if analysis aims to determine the potential outcomes based on varying conditions. What If…'A' occurs what will happen to 'B'. The models applied to the Analytical tool include: sum of data, data averages, polynomial regression and more
​
Goal Seeking Analytics –
is a technique used to work backward from a desired outcome to determine the inputs or conditions needed to achieve that goal. Instead of asking “What will happen if we do X?”, goal-seeking asks: “What do we need to do to make Y happen?”
Join multi model dashboard
SPI allows multiple models i.e (Sales model, Warehouse model) to be combined and allow the sharing of common KPI's.
​
Virtual cubes occur surprisingly frequently in real-world applications. They occur when you have fact tables of different granularities (say one measured at the day level, another at the month level), or fact tables of different dimensionalities (say one on Product, Time and Customer, another on Product, Time and Warehouse), and want to present the results to an end-user who doesn't know or care how the data is structured.
​