The paper presents an example of Instance-Based Learning using a supervised classification

method of predicting selected ductile cast iron castings defects. The test used the algorithm

of k-nearest neighbours, which was implemented in the authors’ computer application. To

ensure its proper work it is necessary to have historical data of casting parameter values

registered during casting processes in a foundry (mould sand, pouring process, chemical

composition) as well as the percentage share of defective castings (unrepairable casting defects).

The result of an algorithm is a report with five most possible scenarios in terms of

occurrence of a cast iron casting defects and their quantity and occurrence percentage in

the casts series. During the algorithm testing, weights were adjusted for independent variables

involved in the dependent variables learning process. The algorithms used to process

numerous data sets should be characterized by high efficiency, which should be a priority

when designing applications to be implemented in industry. As it turns out in the presented

mathematical instance-based learning, the best quality of fit occurs for specific values of

accepted weights (set #5) for number k = 5 nearest neighbours and taking into account the

search criterion according to “product index”.

In many companies, along with the economic development, the use of integrated management systems is becoming more and more common, which are subject to evolution in terms of, inter alia, offered functions and new user requirements. The main purpose of this paper is to compare selected ERP (Enterprise Resource Planning) systems in the field of production planning and control on the example of the automotive industry. The paper presents the contemporary functioning of the automotive industry against the background of issues related to the integrated management systems used in them. The research part presents the proprietary methodology for the assessment of IT systems used in the automotive industry, which included a user survey. The obtained score allowed to indicate the optimal ERP class system supporting production planning and control.