
Performance Analytics
The Ailytic Performance Analytics capability bridges the gap between current and historic plant performance and predicted output with sophisticated dashboards, standard reports, mashups, scorecards, and powerful trending tools.
Dashboards

User configurable dashboards to report schedule performance how you want it to look.
Published schedules

Publish approved schedules and have them dynamically visible to multiple departments including the operation (shop floor, plant environment or external stakeholders) via Web Based visualisation.
Predictive Capacity
Utilisation of shop floor metrics such as OEE, machine capacity attainment, historic benchmarking and current state situational data to accurately model your environment and keep it updated.
Trade Off Analysis

Easily model trade-offs in scenario and schedule performance with dynamic dashboards and KPI graphs. Use powerful Analytic filters to determine where problems and inefficiencies occur.
Capability to Promise
Ensure Capability to Promise for production orders has a high degree of robustness and communicate to stakeholders quickly about changes to order completion dates and times.
Requirements Planning
Highlight projected requirements for production consumables such as raw material, sub-components, dry goods, feedstock, packaging and staff.

Different Types of Analytics
The field of Analytics is sometimes confusing. Ailytic utilises a range of analytic capabilities to deliver value to clients including:





Data Storage (Big Data) – not considered analytics itself (but is commonly misused in analytics classification), it can be described as the analytics baseline requirement for the capture and storage of digital information from source systems in a structured or unstructured way.
Descriptive Analytics – insight from historical data with reporting, scorecards, clustering etc. Most commonly described as Business Intelligence or BI. This is the “What Happened” of the analytics spectrum.
Decisive Analytics – approaches that supports human decisions with visual analytics the user models to reflect reasoning. It builds on descriptive analytics by adding more contextual information representative of natural human reason association.
Predictive Analytics - predictive modelling using statistical and machine learning techniques. These techniques wring unknown insight from complex data. This is the “What is likely to happen”.
Prescriptive Analytics – approaches that recommend decisions using optimisation, simulation and advanced algorithms. This is the “What is the best course of action at some point into the future” or, “based on what we think is likely to happen, what are we going to do about it to achieve our objectives”.