0% found this document useful (0 votes)
4 views11 pages

Project Intm

The project analyzes campaign performance using IBM SPSS Modeler by importing a dataset and applying various nodes for data processing and analysis. Key outcomes include learning data management, cleaning, transformation, and regression modeling to evaluate campaign effectiveness. The analysis highlights the impact of budget allocation on conversions, with visualizations to support findings.

Uploaded by

data82213
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
4 views11 pages

Project Intm

The project analyzes campaign performance using IBM SPSS Modeler by importing a dataset and applying various nodes for data processing and analysis. Key outcomes include learning data management, cleaning, transformation, and regression modeling to evaluate campaign effectiveness. The analysis highlights the impact of budget allocation on conversions, with visualizations to support findings.

Uploaded by

data82213
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

LOVELY PROFESSIONAL UNIVERSITY

Phagwara, Punjab

Predictive Analytics
INTM591

PROJECT
Analyzing Campaign Performance using Derive, Select, and
Regression Nodes

Submitted To: Submitted By:

Ms. NAMAN SAINI SOUMYA GUPTA

Roll No. 11

Registration No:12325960
PROJECT DETAILS
Project Definition

This project focuses on importing a dataset into IBM SPSS Modeler and performing basic
data processing and analysis using different nodes.

Outcomes / Learning

• Learned how to import and manage datasets in SPSS Modeler.

• Gained understanding of using nodes for data preparation and basic analysis.

Required Tool

• IBM SPSS Modeler

Working

• Imported the dataset into SPSS Modeler and created a stream.

• Applied various nodes to clean, transform, and analyze the data.

Data Link

Project Data Link


STEPS PERFORMED
Step 1: Importing Dataset

Imported the dataset into SPSS Modeler using the Source node.

The dataset was successfully loaded into SPSS Modeler using the Source node to begin the
analysis process.

Step 2: Data Understanding


Used the Type node to define and understand data types (nominal, continuous, etc.).

The Type node helped in assigning appropriate data roles and measurement levels for each
variable.
Step 3: Data Cleaning

Applied the Data Audit node to check for missing values and inconsistencies.

The Data Audit node was used to identify missing values, outliers, and overall data quality.

Step 4: Data Transformation

Step 4.1: Adding Derive Node


Added a Derive node to create new variables from existing data.

The Derive node was added to generate new calculated fields for better analysis.
Step 4.2: Creating CTR (Click Through Rate)

Created a new variable CTR using clicks and impressions.

CTR was calculated to measure the effectiveness of campaigns.

Step 4.3: Creating Conversion Rate

Derived a new variable Conversion Rate using conversions and clicks.

Conversion Rate was calculated to evaluate how many clicks turned into actual conversions.
Step 4.4: Cost Per Click (CPC)

Cost spent per click

CPC helps in understanding the cost efficiency of generating clicks.

4.5: Profitability Indicator

Compare conversions vs spend

This helps categorize campaigns based on performance.


Step 5: Data Selection

Step 5.1: Adding Select Node

A Select node was added to filter specific data from the dataset.

The Select node was used to filter and retain only relevant records for analysis.

Step 5.2: Applying Condition

A condition was applied to select specific data (example: Instagram campaigns).


The dataset was filtered to include only Instagram campaigns for focused analysis.

Step 6: Data Visualization

Used Graph node to visualize patterns and relationships.

Graphs were generated to understand trends and patterns in the dataset.


Step 7: Model/Analysis

Applied a basic modelling node like Regression

A regression model was developed by selecting conversions as the target variable and
impressions, clicks, and spend as input variables to analyze their impact on campaign
performance.
The predictor importance chart shows that spend has the highest impact on conversions,
followed by impressions and clicks, indicating that budget allocation plays a key role in
campaign performance.

The regression output displays model summary and ANOVA results, indicating the
relationship between input variables and conversions, along with the overall model
significance.
Step 8.1: Adding Table Node

A Table node was added to display the final processed dataset.

The Table node was used to visualize the final dataset after applying all transformations and
analysis.

You might also like