Data mining techniques have been widely adopted over the last few decades, especially in the business and finance domains. To achieve sustainable benefits from this technique, an organization or company must adopt a standardized process for managing data mining projects, mostly using CRISP-DM. Research has shown that this standard process is often not used as it has been defined to meet the various needs of data mining projects. Understanding company goals and converting them into data mining goals is the primary emphasis of the first phase of CRISP-DM, which is referred to as the Business Understanding (BU) phase. This helps decide the design strategy and the resources that are necessary. After that, the Data Understanding (DU) phase will collect and investigate the preliminary data in order to acquire a better understanding of the data quality. After this, different activities in the Data Preparation (DP) stage are carried out in order to build the final dataset from the raw dataset. These activities may include record and feature selection, data transformation and cleaning for modeling tools, or other similar tasks. The Modeling (MO) phase includes the selection and use of a number of different modeling techniques to the dataset that has been prepared. During the Evaluation (EV) phase, the performance of the model is assessed and reviewed before being placed within the framework of the business objectives. The process of deploying the model in an end-user context is then described in the Deployment (DE) phase of the project. To increase understanding of how the data mining process is used as a reference standard, expanded and adapted in practice, this research reports a case study in finance, especially stock trading. The case study was conducted based on documentation from a portfolio of data mining projects, supplemented by data sourced directly from the Indonesia Stock Exchange. The results reveal that CRISP-DM has impacts and the mechanisms used to predict the stock of PT. Telkom Indonesia (Persero) Tbk (TLKM). This study provides an R2 value of 100% with a MAPE value of 0,0013% when implementing CRISP-DM or similar processes in business and finance.