Introduction: Data mining is the technique in which we analyze data from different sources and perspectives and summarize it into more beneficial or useful information. Additionally, this knowledge or information can be used to reduce costs, increase revenue, or both. There are countless software tools to analyze data from different angles, perspectives or dimensions. Once the data has been analyzed, it is then categorized and summarized to ensure that the appropriate relationships or linearity between the data are identified. To be more specific, data mining is the technique by which we identify correlations or patterns among a large number of variables in relational databases. Data mining is the process of digging and analyzing a huge amount of data sets and extracting more useful and meaningful information from the data. It works primarily on dedicated, knowledge-based decisions. With the help of data mining, more complex and time-consuming questions can be easily answered by extracting information from hidden patterns and predicting values ​​that experts might miss when they exceed their expectations. Below are the steps followed in Data Mining Process:• Organizing Data Sets• Data Sampling• Data Preprocessing and Partitioning• Choosing the Best Fit Model• Validating the Model• Applying the Model to New test data• Analysis of results• Deployment of the model in production• Extraction of knowledge. Any associations, patterns or relationships in the data provide us with the information. Once information or knowledge is extracted from the data, it can be used to predict future trends. In real-world transactional data, data mining provides a link between the two transactional processes...... middle of paper...... and are applied to identify the range of customers likely to respond to the mail, which may be targeted by Telcom Inc., for their new advertising promotions. SOLUTION: Method -1: Application of Logistic Regression: Logistic regression is the most popular and robust classification method. Logistic regression works on the relationship model between predictors and outcomes. It is essentially an extension of linear regression, in which the dependent variable is categorical. Logistic regression can be used for both “classification” and “profiling”. The logistic model can be explained by exploring the relationships between "logit", "odds" and "probability" of the event in context. Running logistic regression: • Data is subjected to a standard partition. • All variables are used for this partition. except Phone_sale are used as input data. • Phone_sale is the output variable.