Reference no: EM133550708

Quesiton: We will use a publicly available dataset on response to direct marketing campaigns of a bank. The marketing campaigns were based on phone contacts with clients. The goal is to assess if the product (bank term deposit) would be subscribed by the client (this is recorded as 'yes'/'no' values in the target variable named 'y'). The dataset has over 45K examples, with 16 other variables: - on client information: age, job, education, marital status, bank balance, whether a client has a housing loan, personal loan, etc.) - related to the last contact of the current campaign: contact type, duration, day and month - related to campaign contacts with the client: number of contacts in this campaign, days since last contact in previous campaign, number of contacts in previous campaigns, outcome of previous campaign. The variables are described in the bank-names.txt file, and data is in the csv file. In the assignment, we will first explore the data to get insights into different variables and how they relate to the outcome. Next we will develop a set of predictive(classification) models and evaluate their performance.