Multifactor analyzer of arbitrary enterprise activity on the IEM platform

WANTED: talented mathematicians for an interesting and monetary contract
Target specialization - matstatistics, mathematical modeling, neural networks.
Task description - below.

The second attempt to humanly formulate the task from the previous posting.

purpose

Development of an application for in-depth analysis of data on the activities of the enterprise, accumulated in the IEM-system . The output is expected to receive an industrial commercial product, a universal analysis solution using Big Data tools that is compatible with all IEM solutions on the Ultimate Solid platform .

General formulation of the problem

Development of a search engine for atypical deviations in the results of the execution of standardized business processes. Initially, it is supposed to use methods of statistics, perhaps - neural networks. And all that is useful too. “Atypicality” of deviations is a tunable parameter of the degree of paranoism of the system (it is the sensitivity, a scalar).

Detailed attempt to describe Wishlist

In the database of the IEM system, complete structured information is collected on the progress of the execution of the enterprise’s business processes in real time.

An example of visualization of the data structure of a real system operator in a financial projection

All history, transactions and other (including aggregated) attributes of processes and process events are saved. The process of executing business processes is strictly standardized and is guaranteed to be closed by the system loop.

The output provides data on the results of a large number of similar procedures (for example, “invoice release” - “receipt of money on the account” - “reservation of goods” - “shipment of goods”, and so a million times). The depth of detail has no fundamental limitations, and is determined by the depth of standardization of real business processes .

Inside the array of structured data, it is proposed to look for non-standard deviations (relative to a given degree of paranoia).

Example: all sales managers have about the same turnover, profitability (profit), but one has an atypically many guarantee return.

Continuous accuracy, consistency and completeness of IEM DB data is guaranteed by the platform. Among other things, they contain information about accounting objects in a variety of reference books and about all occurring events and processes in documents, registers and other mechanisms. All data structures and their connections and interactions are described by metadata stored in the same database in a structured, normalized form.

Ideally, the work of the future application should look like this: access to the desired database is configured, the degree of paranoia is indicated, and that’s all.

The application independently reads metadata that exhaustively describes the business logic of the enterprise, builds chains of business processes, groups them in fact, the results of their development, and in each group searches for atypical ones.

Then he performs some actions with them, understanding of the nature of which falls within the scope of the task (theoretical part), and at the output spits out risk factors - the counterparty, employee, office, order time, or other entity whose behavior information is stored in the system.

Finished about the ideal.

Requirements for the performer

At the current stage, we need a person (group of comrades) who a) are deeply aware of what is at stake, b) build a mathematical methodology for solving the problem in the general case.

The methodology can include methods and heuristics for determining meaningful parameters (or determining indistinguishability for a given set of parameters), defining the process of building data analysis and other technical details.

Given the vagueness and atypical nature of the task, any other adequate proposals from people who can argue their own competence will be considered. The application you are looking for has a high market capacity, so various options for cooperation with a sane contractor are possible.

Technical points

Oracle 12c EE is used as a DBMS.
If necessary, real-time translation can be implemented in Hadoop or similar repositories. But, following the IEM methodology, direct data collection from the application server is the preferred solution.

Proposals to send bigdata@ultimatebusinessware.ru