paul-w-qs/churn_prediction

---
dataset_info:
features:
- name: SALESFORCEACCOUNTID
dtype: string
- name: ACCOUNTING_MONTH
dtype: string
- name: CHURN
dtype: int64
- name: DOWNSELL
dtype: int64
- name: RENEWAL_MONTH
dtype: string
- name: CHURN_SUM
dtype: float64
- name: DOWNSELL_SUM
dtype: float64
- name: CONTRACT_START_DATE
dtype: string
- name: CONTRACT_END_DATE
dtype: string
- name: REGION
dtype: string
- name: TENURE_MONTHS
dtype: int64
- name: MONTHS_UNTIL_EVENT
dtype: int64
- name: DNB_GLOBAL_SALES_REVENUE
dtype: float64
- name: DNB_GLOBAL_EMPLOYEE_COUNT
dtype: int64
- name: DETECTEDSEATSCOUNT
dtype: float64
- name: PRODUCT_ONE
dtype: int64
- name: NUM_PRODUCTS_DAYS_LATE_PREV_90
dtype: int64
- name: LICENSINGSPECIALIST_CHANGE
dtype: int64
- name: CAR_HEALTH_CHECK
dtype: int64
- name: CROSS_SELL_RECENCY
dtype: int64
- name: SEATS_DOWNSELL_RECENCY
dtype: int64
- name: PRODUCT_TWO
dtype: int64
- name: PCT_PRODUCT_THREE_ENABLED
dtype: int64
- name: OTHER
dtype: int64
- name: CUSTOMER_BEHAVIOUR_ONE
dtype: int64
- name: CUSTOMER_BEHAVIOUR_TWO
dtype: int64
- name: PCT_PRODUCT_FOUR_ENABLED
dtype: int64
- name: PRODUCT_FIVE
dtype: int64
- name: PCT_PRODUCT_FIVE_ENABLED
dtype: int64
- name: MAX_SUPPORT_CASE_DAYSTOCLOSE
dtype: int64
- name: SUM_P4FLAG
dtype: int64
- name: PRODUCT_SIX
dtype: int64
- name: CUSTOMER_BEHAVIOUR_THREE
dtype: int64
- name: PRODUCT_THREE
dtype: int64
- name: SALESREP_CHANGE
dtype: int64
- name: SURVEY_AVG_CXI_SCORE
dtype: float64
- name: PCT_PRODUCT_FOUR_BEST_PRACTICE
dtype: int64
- name: EO_ATTENDED
dtype: int64
- name: PRODUCT_SEVEN
dtype: int64
- name: CUSTOMER_BEHAVIOUR_FOUR
dtype: int64
- name: SURVEY_AVG_NPS_SCORE
dtype: float64
- name: CUSTOMER_BEHAVIOUR_FIVE
dtype: int64
- name: PCT_PRODUCT_TWO_ENABLED
dtype: int64
- name: PCT_PRODUCT_SIX_ENABLED
dtype: int64
- name: CUSTOMER_BEHAVIOUR_SIX
dtype: int64
- name: PRODUCT_EIGHT
dtype: int64
- name: PRODUCT_NINE
dtype: int64
- name: PRODUCT_TEN
dtype: int64
- name: CUSTOMER_BEHAVIOUR_SEVEN
dtype: int64
- name: PRODUCT_ELEVEN
dtype: int64
- name: PRODUCT_TWELVE
dtype: int64
- name: PRODUCT_THIRTEEN
dtype: int64
- name: CUSTOMER_BEHAVIOUR_EIGHT
dtype: int64
- name: PRODUCT_FOURTEEN
dtype: int64
- name: PRODUCT_FIFTEEN
dtype: int64
- name: PRODUCT_DOWNSELL_RECENCY
dtype: int64
- name: UPSELLMANAGER_CHANGE
dtype: int64
- name: MAX_SUPPORT_CASE_TIMETOFIRSTRESPONSE
dtype: int64
- name: SURVEY_AVG_CASE_MOOD_SCORE
dtype: float64
- name: PCT_PRODUCT_THREE_BEST_PRACTICE
dtype: int64
- name: CASES_CREATED_FIRST_30_AFTER_IMPLEMENTATION
dtype: int64
- name: PRODUCT_FOUR
dtype: int64
- name: PCT_PRODUCT_TWO_BEST_PRACTICE
dtype: int64
- name: IMPLEMENTATION_MONTHS_RUNNING_TOTAL
dtype: int64
- name: CAR_CHURN_OR_RISK_DISCUSSION
dtype: int64
- name: PRODUCT_SIXTEEN
dtype: int64
- name: PRODUCT_SEVENTEEN
dtype: int64
- name: RATIO_SEATS_ACTIVE
dtype: float64
- name: MONTHLY_PRODUCT_COUNT
dtype: int64
- name: ARR
dtype: float64
- name: SUPPORT_CASE_NUMBEROFSLABREACHES
dtype: int64
- name: AVG_SEATS
dtype: int64
- name: CUSTOMER_BEHAVIOUR_NINE
dtype: int64
- name: CONTRACT_LENGTH
dtype: int64
- name: CUSTOMER_BEHAVIOUR_TEN
dtype: int64
- name: PRODUCT_EIGHTEEN
dtype: int64
- name: CUSTOMER_BEHAVIOUR_ELEVEN
dtype: int64
- name: SEATS_UPSELL_RECENCY
dtype: int64
- name: PRODUCT_NINETEEN
dtype: int64
- name: ACCOUNTMANAGER_CHANGE
dtype: int64
- name: PCT_PRODUCT_NINE_ENABLED
dtype: int64
- name: PRODUCT_TWENTY
dtype: int64
- name: PRODUCT_TWENTYONE
dtype: int64
- name: PRODUCT_TWENTYTWO
dtype: int64
- name: PRODUCT_TWENTYTHREE
dtype: int64
- name: SUM_P0FLAG
dtype: int64
- name: SUM_P1FLAG
dtype: int64
- name: SUM_P2FLAG
dtype: int64
- name: SUM_P3FLAG
dtype: int64
- name: BACKLOG
dtype: int64
- name: AVG_SUPPORT_CASE_PRIORITY_SCORE
dtype: float64
- name: COMPETITOR_SEATS
dtype: int64
- name: RPU
dtype: float64
- name: SECTOR
dtype: string
- name: P0123_FLAGS
dtype: int64
- name: ARR_DIV_SEATS
dtype: float64
splits:
- name: train
num_bytes: 85464346
num_examples: 100000
download_size: 7102198
dataset_size: 85464346
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "churn_prediction"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集概述

特征信息

数据集包含以下特征及其数据类型：

• SALESFORCEACCOUNTID: 字符串
• ACCOUNTING_MONTH: 字符串
• CHURN: 整数
• DOWNSELL: 整数
• RENEWAL_MONTH: 字符串
• CHURN_SUM: 浮点数
• DOWNSELL_SUM: 浮点数
• CONTRACT_START_DATE: 字符串
• CONTRACT_END_DATE: 字符串
• REGION: 字符串
• TENURE_MONTHS: 整数
• MONTHS_UNTIL_EVENT: 整数
• DNB_GLOBAL_SALES_REVENUE: 浮点数
• DNB_GLOBAL_EMPLOYEE_COUNT: 整数
• DETECTEDSEATSCOUNT: 浮点数
• PRODUCT_ONE: 整数
• NUM_PRODUCTS_DAYS_LATE_PREV_90: 整数
• LICENSINGSPECIALIST_CHANGE: 整数
• CAR_HEALTH_CHECK: 整数
• CROSS_SELL_RECENCY: 整数
• SEATS_DOWNSELL_RECENCY: 整数
• PRODUCT_TWO: 整数
• PCT_PRODUCT_THREE_ENABLED: 整数
• OTHER: 整数
• CUSTOMER_BEHAVIOUR_ONE: 整数
• CUSTOMER_BEHAVIOUR_TWO: 整数
• PCT_PRODUCT_FOUR_ENABLED: 整数
• PRODUCT_FIVE: 整数
• PCT_PRODUCT_FIVE_ENABLED: 整数
• MAX_SUPPORT_CASE_DAYSTOCLOSE: 整数
• SUM_P4FLAG: 整数
• PRODUCT_SIX: 整数
• CUSTOMER_BEHAVIOUR_THREE: 整数
• PRODUCT_THREE: 整数
• SALESREP_CHANGE: 整数
• SURVEY_AVG_CXI_SCORE: 浮点数
• PCT_PRODUCT_FOUR_BEST_PRACTICE: 整数
• EO_ATTENDED: 整数
• PRODUCT_SEVEN: 整数
• CUSTOMER_BEHAVIOUR_FOUR: 整数
• SURVEY_AVG_NPS_SCORE: 浮点数
• CUSTOMER_BEHAVIOUR_FIVE: 整数
• PCT_PRODUCT_TWO_ENABLED: 整数
• PCT_PRODUCT_SIX_ENABLED: 整数
• CUSTOMER_BEHAVIOUR_SIX: 整数
• PRODUCT_EIGHT: 整数
• PRODUCT_NINE: 整数
• PRODUCT_TEN: 整数
• CUSTOMER_BEHAVIOUR_SEVEN: 整数
• PRODUCT_ELEVEN: 整数
• PRODUCT_TWELVE: 整数
• PRODUCT_THIRTEEN: 整数
• CUSTOMER_BEHAVIOUR_EIGHT: 整数
• PRODUCT_FOURTEEN: 整数
• PRODUCT_FIFTEEN: 整数
• PRODUCT_DOWNSELL_RECENCY: 整数
• UPSELLMANAGER_CHANGE: 整数
• MAX_SUPPORT_CASE_TIMETOFIRSTRESPONSE: 整数
• SURVEY_AVG_CASE_MOOD_SCORE: 浮点数
• PCT_PRODUCT_THREE_BEST_PRACTICE: 整数
• CASES_CREATED_FIRST_30_AFTER_IMPLEMENTATION: 整数
• PRODUCT_FOUR: 整数
• PCT_PRODUCT_TWO_BEST_PRACTICE: 整数
• IMPLEMENTATION_MONTHS_RUNNING_TOTAL: 整数
• CAR_CHURN_OR_RISK_DISCUSSION: 整数
• PRODUCT_SIXTEEN: 整数
• PRODUCT_SEVENTEEN: 整数
• RATIO_SEATS_ACTIVE: 浮点数
• MONTHLY_PRODUCT_COUNT: 整数
• ARR: 浮点数
• SUPPORT_CASE_NUMBEROFSLABREACHES: 整数
• AVG_SEATS: 整数
• CUSTOMER_BEHAVIOUR_NINE: 整数
• CONTRACT_LENGTH: 整数
• CUSTOMER_BEHAVIOUR_TEN: 整数
• PRODUCT_EIGHTEEN: 整数
• CUSTOMER_BEHAVIOUR_ELEVEN: 整数
• SEATS_UPSELL_RECENCY: 整数
• PRODUCT_NINETEEN: 整数
• ACCOUNTMANAGER_CHANGE: 整数
• PCT_PRODUCT_NINE_ENABLED: 整数
• PRODUCT_TWENTY: 整数
• PRODUCT_TWENTYONE: 整数
• PRODUCT_TWENTYTWO: 整数
• PRODUCT_TWENTYTHREE: 整数
• SUM_P0FLAG: 整数
• SUM_P1FLAG: 整数
• SUM_P2FLAG: 整数
• SUM_P3FLAG: 整数
• BACKLOG: 整数
• AVG_SUPPORT_CASE_PRIORITY_SCORE: 浮点数
• COMPETITOR_SEATS: 整数
• RPU: 浮点数
• SECTOR: 字符串
• P0123_FLAGS: 整数
• ARR_DIV_SEATS: 浮点数

数据分割

• 训练集:
  • 字节数: 85464346
  • 样本数: 100000

数据集大小

• 下载大小: 7102198 字节
• 数据集大小: 85464346 字节

配置

• 默认配置:
  • 数据文件路径: data/train-*