Scribd
Upload
311 views9 pages

Churn Prediction and ML

Uploaded by

harshita9503
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
311 views9 pages

Churn Prediction and ML

Uploaded by

harshita9503
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
You are on page 1/ 9

Machine learning is a subset of artificial intelligence (AI)

that focuses on the development of algorithms and


statistical models that enable computers to learn from and
make predictions or decisions based on data, without being
explicitly programmed to do so. In essence, machine
learning algorithms learn patterns and relationships from
data and use this knowledge to make predictions or
decisions on new, unseen data
01 02 03 04
Supervised Learning: the Unsupervised Learning: the Semi-Supervised Learning: Reinforcement Learning:
algorithm is trained on a algorithm is trained on an Semi-supervised learning Reinforcement learning
labeled dataset, where unlabeled dataset, where combines elements of involves training an agent
each example is paired the goal is to uncover both supervised and to interact with an
with the correct output. hidden patterns or unsupervised learning. The environment in order to
The algorithm learns to structures within the data. algorithm is trained on a maximize some notion of
map inputs to outputs, Unsupervised learning dataset that contains cumulative reward. The
making predictions or algorithms learn to group both labeled and agent learns through trial
decisions based on the similar data points unlabeled examples and error, receiving
input data together or discover feedback in the form of
meaningful relationships rewards or penalties for its
without explicit guidance.. actions.
CLASSIFICATION
Classification is a fundamental task in
machine learning where the goal is to
categorize input data into one of several
predefined classes or categories.

The classification model learns patterns


from labeled training data and uses this
knowledge to predict the class labels of
unseen data.
TYPES OF CLASSIFICATION ALOGIRTHM
Logistic Regression:
logistic regression is a linear Decision Trees:
model for binary
Decision trees recursively
classification.
split the feature space into
regions, with each split
Random Forests: being based on the feature
that best separates the
Random forests are an
instances into their
ensemble learning
respective classes.
technique that combines
multiple decision trees to
improve predictive
performance and
robustness.
CHURN PREDICTION
Helps to identify the customer who are going to
cancel their subscription or shitfing to the
competitors
Identifying churn before it happens helps
businesses take proactive action to retain
customers
A high churn rate indicates that a business is
losing significant customers, certainly more than
it is bringing in.
Agenda
To Predict Customer Churn
Need to Predict Customer Churn
New Customer acquisition cost can be higher
so that best way to increase a company’s profit is
to retain the existing customer
To find out the reason for churn
Risk Management
Maximise Customer Lifetime Value
Customer Satisfaction Improvement
Reasons for High Churn Rates
Product/ Service Quality Customer satisfaction scores

FEATURES
REASNOS

Customer Engagement Usage Patterns

Billing & Payments Issues Frequency of billing errors

Changing Customer needs Customer behaviour

Negative Publicity Sentiment analysis of reviews


CHURN PREDICTION
PROCESS

Data Collection: Gather relevant data from various sources including customer databases, transaction records,
interaction logs, demographic information, customer service records, and any other relevant sources
1
Data Processing: Cleanse and process the data to handle missing values, outliers, and inconsistencies. with
Techniques like imputation, outliers detection, Data Normalisation and Standardistion.
2
Features Selection: Extract or create relevant features from the raw data that are predictive of churn.
3
Exploratory Data Analysis(EDA): Conduct exploratory data analysis to gain insights into the distribution of
features, correlations between variables, and patterns in the data that may be indicative of churn behaviour.
4
Data Splitting: Split the dataset into training and testing sets to evaluate the performance of the
churn prediction model.
5
CHURN PREDICTION
PROCESS

Model Selection: Choose appropriate machine learning algorithms for churn prediction, considering factors
such as interpretability, scalability, and performance.
6
Model Training: Train the selected models using the training data. During training, the models learn patterns
from the data that can be used to predict churn.
7
Model Evaluation: Evaluate the performance of the trained models using the testing dataset. Use
appropriate evaluation metrics such as accuracy, precision, F1-score, ROC AUC, or lift curve to assess the model's
predictive power. 8
Prediction: predict the churn with the help of modals
9
Actions: Take proactive actions to retain the customers.
10

You might also like