•Data preparation is the foundation of data mining. Field data are huge and noisy. The proper data reflecting reservoir properties need to be acquired. In addition to some common parameters, such as porosity and permeability, two new parameters – a fluid mobility factor and the maximum inscribed rectangular of net pay (MIRNP) – are proposed. Additionally, three parameters to represent the production performance of wells are proposed: the peak value, effective life cycle and effective yield, because each well has a different production period length and fluctuating daily production rates.•Data filtration is important for good results in data analysis, and the extracted data need to filter further before data mining. The fuzzy ranking method is used to rank the importance of the identified reservoir properties in terms of oil production parameters. Variables with less contribution are removed and appropriate reservoir properties are chosen, which implicitly helps in improving the results of data mining and reduces a large amount of computation.•Association rule mining is used to discover relationships between the oil production and various reservoir properties from reservoir data for CHOPS. The proposed methods have been applied for 118 wells in the Sparky Formation of the Lloydminster heavy oil field in Alberta to find rules and then four other wells in the study area that satisfy the selection criteria were collected to validate the association rules discovered. The result shows that the production performance of wells in the area could be described and predicted by using the found relations.