Published February 13, 2012
| Version v1
Dataset
Open
Bank Marketing Dataset (UCI) - Test Upload
Creators
Description
This dataset is related to direct marketing campaigns conducted by a Portuguese banking institution, with campaigns relying on phone calls. Often multiple contacts with the same client were necessary to determine whether they would subscribe ('yes') or not ('no') to a bank term deposit. The dataset includes four files:
- bank-additional-full.csv: Contains all 41,188 examples with 20 input features, organized chronologically from May 2008 to November 2010, closely aligned with the data analyzed in [Moro et al., 2014].
- bank-additional.csv: A subset of 4,119 examples (10% of the full data), randomly selected, with 20 input features.
- bank-full.csv: The older version of the dataset, comprising all examples (41,188) with 17 input features, also organized chronologically.
- bank.csv: A 10% random subset of the older version, containing 4,119 examples and 17 input features.
The smaller subsets are designed for testing computationally intensive machine learning algorithms (e.g., SVM). The primary classification objective is to predict whether a client will subscribe to a term deposit ('yes' or 'no'), based on the target variable y.
Files
bank+marketing.zip
Files
(1.0 MB)
Name | Size | Download all |
---|---|---|
md5:3a3c6c4189975ea1f3040dbd60ad106c
|
1.0 MB | Preview Download |