<![CDATA[Data governance is crucial to ensure that traffic data is collected, managed, and used accurately to support quick, precise, and evidence-based decision-making in traffic management. The main challenge faced by many transportation agencies is the lack of an established data governance framework, which means that the utilization of Average Daily Traffic (ADT) data remains descriptive and does not yet support predictive planning. This situation results in traffic management being reactive and less effective in handling vehicle surges during critical periods. This study aims to implement a data governance framework in traffic management by developing comprehensive data management practices, including data acquisition, data quality assurance, and data-driven decision-making through ADT data prediction using the Python programming language. The approach applied is simple linear regression, applied to four years of historical ADT data to create a systematic and accountable prediction model, in accordance with data governance principles: accuracy, affordability, and policy relevance. The data were coded as numerical variables and analyzed to estimate future vehicle volumes clearly and replicably. The study's findings indicate that a Python-based prediction model, when integrated into the data governance structure, can provide more accurate, measurable, and policy-relevant traffic volume projections. This contributes to improving the quality of Data Governance, particularly in providing reliable and relevant information for strategic decisions. By incorporating this prediction system into the data governance framework, the relevant agencies are expected to be able to plan more proactive traffic management strategies, including vehicle flow regulation, road capacity optimization, and effective resource allocation based on structured understanding and strong data governance.]]>
