CatCoin项目数据集

CatCoin项目数据集是由西班牙主要银行的真实客户交易数据组成，包含30,844条交易描述，主要使用西班牙语，涵盖2017年8月至2018年2月的时间段。该数据集通过CoinScrap平台收集，用于训练和测试基于自然语言处理和机器学习算法的银行交易描述分类系统。数据集包含交易描述、金额、日期等属性，并标记有分类标签，旨在解决个人财务管理中的交易自动分类问题。

The CatCoin project dataset consists of real customer transaction data from major Spanish banks, containing 30,844 transaction descriptions predominantly in Spanish and spanning the period from August 2017 to February 2018. Collected via the CoinScrap platform, this dataset is designed to train and test banking transaction description classification systems built on natural language processing (NLP) and machine learning (ML) algorithms. The dataset includes attributes such as transaction descriptions, amounts and dates, with annotated classification labels, aiming to solve the problem of automated transaction classification in personal financial management.