In order to enhance the efficacy of future marketing campaigns for a financial institution, it is imperative to analyze the patterns and outcomes of previous marketing endeavors. This analysis enables the identification of optimal strategies to implement, leading to improved success in future campaigns.
The dataset utilized in this project comprises 21 features and 39,188 samples, providing a comprehensive foundation for analysis and decision-making.
Features Description:
AGE: A numerical column representing the customer's age.
JOB: A categorical column indicating the customer's employment status.
Marital_status: A categorical column capturing the customer's marital status.
Education: A grouping column illustrating the customer's educational background.
Default: Indicates whether the customer has any defaulted bank credit.
Housing: Determines if the customer has obtained a housing loan.
Loan: Indicates if the customer has received a personal loan.
Contact: Specifies the communication channel used to contact the customer, either cellular or telephone.
Month: Indicates the month in which the customer was last contacted.
Day_of_week: Determines the day of the week when the last contact with the customer occurred.
Campaign: The number of calls made to the customer during the current campaign.
P_days: The number of days since the last customer contact for the previous campaign. 999 denotes no prior contact.
Previous: The number of calls made to the customer during previous campaigns.
P_outcome: The outcome of previous campaigns for the client.
emp_var_rate: The rate of employment changes over a three-month period.
cons_price_idx: The consumer price index within a one-month timeframe.
cons_conf_idx: The consumer confidence index within a one-month timeframe.
euribor3m: Bank interest rates for European interbank loans.
nr.employed: The number of employees during a three-month period.
y: Indicates whether the person responded positively to the bank's investment campaign or not.
This dataset, as described by Moro et al. (2014), enables a data-driven approach to predict the success of bank telemarketing campaigns. By examining the relationships between various features and the campaign outcomes, valuable insights can be gained to inform future marketing strategies.
The findings from this analysis contribute to evidence-based decision-making, enabling financial institutions to optimize their marketing efforts and enhance campaign success rates.
Reference: Moro, S., Cortez, P., & Rita, P. (2014). A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62, 22-31. https://doi.org/10.1016/j.dss.2014.03.001
[Moro et al., 2014] S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, Elsevier, 62:22-31, June 2014. https://doi.org/10.1016/j.dss.2014.03.001