Purpose: The aim of this study is to design a framework for modeling digital marketing attribution using Python in Iran, identify its key drivers, determine their hierarchical relationships and levels using ISM-MICMAC, and demonstrate the practical application of Python in allocating value to marketing channels and optimizing marketing budgets.

Method: This exploratory, descriptive, and applied developmental study adopted a mixed methods approach. In the qualitative phase, thematic analysis of previous literature and interviews with 21 academic and professional experts identified 52 influential factors. Participants were selected through judgmental and snowball sampling. In the quantitative phase, these factors were evaluated using a Likert scale questionnaire, a binomial test, and the content validity ratio, resulting in the confirmation of nine key drivers. Interpretive structural modeling established the hierarchical relationships among the confirmed factors. Cross impact matrix multiplication applied to classification was then used to examine their driving power and dependence.

Results: Marketer intelligence and acumen emerged as the most influential driver, whereas the ability to understand and analyze big data exhibited the highest dependence. The factors were arranged into five hierarchical levels and classified into four categories: autonomous, dependent, linkage, and independent. Programming education, information technology, and sales optimization were identified as linkage factors connecting independent and dependent drivers within the model.

Conclusions: Developing digital marketing using Python requires investment in workforce education, information technology infrastructure, and transparency in marketing performance. The proposed model can help managers prioritize development initiatives, allocate budgets efficiently, and design multichannel marketing strategies. In addition to identifying and hierarchically structuring the drivers using ISM-MICMAC, a reproducible implementation example of channel attribution modeling in Python was presented to demonstrate the practical application of the framework in budget allocation and improving marketing performance transparency.