Scribd
Upload
51 views13 pages

Credit Card Fraud Detection Using Random Forest Algo

The document discusses using a Random Forest algorithm for credit card fraud detection. It describes the types of credit card fraud, challenges in detection, how the Random Forest algorithm works, and its implementation for fraud detection including data preprocessing, training and testing a model, and evaluating results.

Uploaded by

Atharva Gokhare
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
51 views13 pages

Credit Card Fraud Detection Using Random Forest Algo

The document discusses using a Random Forest algorithm for credit card fraud detection. It describes the types of credit card fraud, challenges in detection, how the Random Forest algorithm works, and its implementation for fraud detection including data preprocessing, training and testing a model, and evaluating results.

Uploaded by

Atharva Gokhare
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/ 13

Credit Card Fraud

Detection Using Machine


Learning
Algorithm(RandomForest)

Presented by: Atharva Gokhare


Introduction
Fraud can be defined as criminal deception with intent of
acquiring financial gain.

Types of credit card fraud:


Inner Card Fraud : Done by using false identity
External Card Fraud: Done by using stolen card

How are these frauds recognized:


Location of usage
Items bought from it
Frequency of usage
Amount of usage
Challenges:
The data is highly skewed.
Normal Machine Learning Algorithms would give 99% + accuracy.
We can still get 99.8% accuracy if we classify all frauds as legitimate.
RANDOM FOREST ALGORITHM:

Random Forest is also called as Random Decision Forest which is used for
Classification, Regression and other tasks that are performed by constructing
multiple decision trees.
This Random Forest Algorithm (RFA) is based on supervised learning and the
major advantage of this algorithm is that it can be used for both Classification
and Regression.
Random Forest Algorithm gives you better accuracy when compared with all
other existing systems and this is most commonly used algorithm.
The use of Random forest algorithm in credit card fraud detection can give
you accuracy of about 90 to 95%.
RFA IMPLEMENTATION IN CREDIT CARD FRAUD DETECTION

In credit card fraud detection the Random Forest Algorithm gives better accuracy in
results.
First all the dataset will be collected and analyzed. During analysis process all the
duplicate values and also the null values will be removed from the dataset.
Now the dataset will be preprocessed based on the amount and transaction time
for finding the accuracy of the resultant dataset.
After the pre processing of dataset into amount and transaction time now the dataset
will be divided into two categories. The dataset is classified in two categories as trained
data and test dataset.
Here for dataset classification we use a software called ‘Scikit-learn’.
After the pre processing of the dataset now we apply the Random Forest
Algorithm. By applying Random Forest Algorithm the pre processed dataset will be
analyzed again and then a confusion matrix will be obtained.
In confusion matrix the dataset will be partitioned into four blocks as True
Positive(TP), True Negative(TN), False Positive(FP) and False Negative(FN).

Now the dataset will be partitioned continuously until all the data is validated.

Now all these partitioned data will be evaluated and finally it will be represented
as separate graphs.

These separate graphs will give only less accuracy about the resultant dataset.

So in order to obtain better accuracy we use Random Forest Algorithm where it


takes all the graph values and give us only necessary values with better accuracy
when compared with all other algorithms.
System Architecture:
In our architecture first we have a credit card dataset where this contains all the details about credit
card.
But here we take only Amount and Transaction time for analysis and pre processing of dataset.The
next step is the process of data cleaning where the dataset will be analyzed and all the duplicate and
null values will be eliminated from the dataset taken.
The next step is the data partition where the credit card dataset will be partitioned into two partitions
as trained dataset and testing dataset.
After that Random Forest Algorithm will be applied and a confusion matrix will be obtained. Now the
performance analysis will be done on the obtained confusion matrix.
Implementation Modules:
Output Screenshots:
THE END

You might also like