Real Dataset From Broadband Customers of a Brazilian Telecom Operator
收藏资源简介:
This dataset includes information from broadband users of a telecom operator located in Brazil. It includes modem parameters extracted from the operator's Network Management System (NMS) and customer complaint information extracted from the operators' CRM. The modem is a Optical Network Terminal (OLT), located in customer premises, responsible for providing Wi-Fi for the customer, and is the terminal for the optical fiber in a Gigabit Passive Optical Network (GPON) Collection Date: January/23 to June/23 The modem data was collected for 6 months for a set of specific customers. At the end of the period, data from this set of customers were collected using the Customer Relationship Management (CRM) system. If the customer complained during that period, we filtered the modem parameters on the day of the last complaint. If the customer has not complained within the period, we use the parameters from the last parameter collection from its modem. The file has the raw data in a Comma-Separated Values (CSV) format using UTF-8 encoding. The file has a set of different parameters. "Customer ID" - A unique ID for the customer in the dataset. The customer's personal information was anonymized. "Latency" - Value of the latency the user is experiencing. Latency is the time it takes for data to get from one network point to another. "Jitter" - Value of the jitter (variation in latency) the user is experiencing. "Packet Loss" - The percentage (%) of packets lost during the transmission "Channel2_quality" - The Quality of the customer's 2.4GHz channel, rated on a scale of 1 to 5 by the modem "Channel5_quality" - The Quality of the customer's 5GHz channel, rated on a scale of 1 to 5 by the modem "N distant devices" - The Number of devices far from the modem (more than 10 m) "CRM_Complaint?" - Indicates whether the user complains (value = 1) about its broadband experience or not (value = 0).
本数据集涵盖巴西某电信运营商宽带用户的相关信息,包含从该运营商网络管理系统(Network Management System, NMS)提取的调制解调器(modem)参数,以及从运营商客户关系管理系统(Customer Relationship Management, CRM)提取的用户投诉信息。此处所指的调制解调器实为部署于用户驻地的光网络终端(Optical Network Terminal, OLT),负责为用户提供Wi-Fi接入服务,同时是吉比特无源光网络(Gigabit Passive Optical Network, GPON)中的光纤终端设备。 数据采集时段为2023年1月至2023年6月,针对特定用户群体连续采集6个月的调制解调器参数,并于该时段结束后通过客户关系管理系统获取该批用户的关联数据。数据处理规则如下:若用户在此期间发起过宽带体验投诉,则取其最后一次投诉当日的调制解调器参数;若用户未发起投诉,则采用该用户调制解调器最后一次采集的参数。 本数据集以UTF-8编码的逗号分隔值(Comma-Separated Values, CSV)格式存储原始数据,包含以下多类参数: - "Customer ID":数据集中用户的唯一标识符,用户个人信息已完成匿名化处理。 - "Latency":用户当前遭遇的网络延迟值,延迟指数据从一个网络节点传输至另一节点所需的时长。 - "Jitter":用户当前遭遇的抖动(延迟波动幅度)值。 - "Packet Loss":传输过程中的丢包百分比(%)。 - "Channel2_quality":用户2.4GHz信道的质量评分,由调制解调器基于1至5分的量表进行评定。 - "Channel5_quality":用户5GHz信道的质量评分,由调制解调器基于1至5分的量表进行评定。 - "N distant devices":距离调制解调器10米以上的远端设备总数量。 - "CRM_Complaint?":标识用户是否发起过宽带体验投诉,取值为1代表已投诉,取值为0代表未投诉。



