Dark Mode
E-commerce Conversion Predictive Modelling Data
E-commerce & Online Transactions
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Simulates a customer conversion scenario, focusing on potential leads and their engagement with a hypothetical business. It is a synthetic resource created specifically for developing and testing machine learning models that predict lead conversion or the likelihood of a desired action being taken. The data tracks various interactions, sales efforts, and demographic characteristics. It is highly valuable for data analysis, optimizing marketing strategies, and improving sales performance by identifying key conversion drivers. The dataset includes a binary target variable indicating whether a lead successfully converted based on predefined criteria related to engagement, behavior, age, and location.
Columns
The dataset includes 19 features detailing lead activity and characteristics:
- LeadID: A unique identifier for each potential customer record.
- Age: The lead's age, ranging from 20 to 60.
- Gender: Binary classification, with a near-equal split between Female and Male users.
- Location: Geographic location, with a focus on major cities in Pakistan.
- LeadSource: The original source that generated the lead (e.g., Social Media, Organic).
- TimeSpent (minutes): The duration of engagement, ranging from 5 to 60 minutes.
- PagesViewed: The total number of pages visited, ranging from 2 to 15.
- LeadStatus: The current qualification status of the lead (e.g., Hot, Warm).
- EmailSent: The total count of emails sent to the lead, ranging from 0 to 10.
- DeviceType: The device used by the lead (e.g., Tablet, Mobile).
- ReferralSource: The source from which the user was referred (e.g., Direct, Google).
- FormSubmissions: The count of forms submitted, ranging from 0 to 5.
- Downloads: The number of files or resources downloaded, ranging from 0 to 3.
- CTR_ProductPage: The Click-Through Rate on the product pages, ranging from 0.1 to 0.8.
- ResponseTime (hours): The time taken for initial follow-up, ranging from 1 to 24 hours.
- FollowUpEmails: The count of follow-up emails sent, ranging from 0 to 10.
- SocialMediaEngagement: A metric quantifying social media interaction, ranging from 20 to 200.
- PaymentHistory: Indicates the lead’s prior history of payments (No Payment or Good), with an equal distribution.
- Conversion (Target): The binary outcome variable (1 for converted, 0 for not converted).
Distribution
The data file is provided in CSV format and is named
customer_conversion_testing_dataset.csv, with a size of 2.3 MB. The structure includes 19 distinct columns and 26.1k records. The dataset is fully validated, showing 100% data validity with zero missing or mismatched values across all fields.Usage
This data product is suited for several advanced applications:
- Developing and fine-tuning predictive models for customer conversion likelihood (binary classification).
- Performing detailed data analysis to determine the effectiveness of various lead sources and engagement techniques.
- Optimising digital marketing and sales funnel strategies by benchmarking lead behavior.
- Building lead scoring mechanisms based on attributes like age, time spent, and response time.
Coverage
Geographic Scope: The dataset focuses geographically on lead locations within major cities in Pakistan.
Demographic Scope: It covers leads across a significant adult age range (20 to 60) and features a balanced gender distribution.
Update Frequency: The data is expected to be updated annually.
License
CC0: Public Domain
Who Can Use It
- Data Scientists: For training and evaluating machine learning algorithms specifically targeting conversion prediction.
- Marketing Professionals: To identify high-value leads and segment audiences based on predicted conversion probability.
- Business Analysts: To gain insights into customer journey metrics, such as time spent and form submissions, and their impact on sales outcomes.
Dataset Name Suggestions
- Stuffmart Customer Conversion Prediction Dataset
- Synthetic Lead Engagement and Conversion Metrics
- E-commerce Conversion Predictive Modelling Data
Attributes
Original Data Source:E-commerce Conversion Predictive Modelling Data
QUALITYLoading...