晋江地区课程老师方案生成数量预测数据

课程老师作为在线教育企业课程推广与销售的核心力量，其业务成效直接关系到在线教育企业的发展。围绕晋江地区课程老师上月的6项关键指标 —— 云产品总分享数（次）、云产品总浏览数（次）、云产品有效访问人数（次），云共享总分享数（次）、云共享总浏览数（次）、AI 客服总咨询数（次）来建立本月预测方案生成数量（个）的预测模型。该模型通过深度挖掘在线教育行业企业课程老师的行为数据，精准预测学习课程方案生成量。对行业企业而言有助于优化资源配置，提升老师能力：为预测高方案生成量的老师提前匹配流量、技术支持等资源，对预测方案生成少的老师，结合其分享量低、浏览数据差等问题，开展定向培训（如云共享传播技巧、高浏览内容设计），针对性提升传播动能。对于在线教育行业相关企业，可据此深入理解课程推广与销售的关系，推动课程老师转发、分享课程，优化客服话术、推送高转化课程包，为将互动转化为付费与续费，显著提升转化效率提供数据支持。1、数据来源于本企业内部，通过采集：分析时间、课程老师ID、地区、数据分析时间段、云产品总分享数（次）、云产品总浏览数（次）、云产品有效访问人数（次），云共享总分享数（次）、云共享总浏览数（次）、AI 客服总咨询数（次）建立方案预测模型，来计算课程老师本月预测方案生成数量（个）。
2、对采集到的数据进行脱敏、清洗、去除异常值。建立本月预测方案生成数量（个）模型。
本月预测方案生成数量（个）=0.791 - 0.053*云产品总分享数（次） + 0.185*云产品总浏览数（次） - 0.131*云产品有效访问人数（次） + 0.176*云共享总分享数（次） + 0.043*云共享总浏览数（次） + 0.258*AI客服总咨询数（次） 。
3、此模型有助于所有在线教育行业企业运营策划。为在线教育行业的稳健发展提供数据支持。

Course instructors are the core driving force for course promotion and sales of online education enterprises, and their business performance directly affects the development of such enterprises. Focusing on the 6 key indicators of course instructors in the Jinjiang area from the previous month — total number of cloud product shares, total number of cloud product views, total number of valid visitors to cloud products, total number of cloud sharing shares, total number of cloud sharing views, and total number of AI customer service inquiries — we establish a prediction model for the predicted number of plan generation this month. This model, by deeply mining the behavioral data of course instructors from online education enterprises, accurately predicts the volume of course plan generation. For enterprises in the industry, it helps optimize resource allocation and improve instructor capabilities: match resources such as traffic and technical support in advance for instructors predicted to have high plan generation volume; for instructors with low predicted plan generation volume, carry out targeted training (such as cloud sharing promotion skills and high-traffic content design) based on their low share volume and poor view data, so as to enhance communication momentum in a targeted manner. For relevant enterprises in the online education industry, this can help them deeply understand the relationship between course promotion and sales, promote course instructors to forward and share courses, optimize customer service scripts, push high-conversion course packages, and provide data support for converting interactions into payments and renewals, thereby significantly improving conversion efficiency.

1. The data is sourced from the internal systems of our enterprise. By collecting metrics including analysis time, course instructor ID, region, data analysis time period, total number of cloud product shares, total number of cloud product views, total number of valid visitors to cloud products, total number of cloud sharing shares, total number of cloud sharing views, and total number of AI customer service inquiries, we establish a plan prediction model to calculate the predicted number of plan generation per course instructor this month.
2. The collected data is subjected to desensitization, cleaning and outlier removal. A model for predicting the number of plan generation this month is established.
The formula of the model is: Predicted number of plan generation this month = 0.791 - 0.053 × Total number of cloud product shares + 0.185 × Total number of cloud product views - 0.131 × Total number of valid visitors to cloud products + 0.176 × Total number of cloud sharing shares + 0.043 × Total number of cloud sharing views + 0.258 × Total number of AI customer service inquiries.
3. This model is beneficial for operational planning of all online education enterprises, providing data support for the steady development of the online education industry.

搜集汇总

背景与挑战

背景概述

该数据集是晋江地区课程老师方案生成数量的预测数据，包含551条记录，每月更新，用于基于云产品分享、浏览、AI客服咨询等6项指标建立线性回归模型，预测本月方案生成量。其应用场景聚焦于在线教育企业，通过模型结果优化老师资源配置和培训，提升课程推广效率，支持行业稳健发展。