Difference between revisions of "Watch me Build a Cybersecurity Startup"

From
Jump to: navigation, search
(→‎Credit Card Fraud Detection | Nick Walker)
(→‎DharmaSecurity)
Line 48: Line 48:
  
 
=== Credit Card Fraud Detection | Nick Walker ===
 
=== Credit Card Fraud Detection | Nick Walker ===
−
* [http://github.com/nickwalker037/Credit-Card-Fraud-Detection Credit Card Fraud Detection | Nick Walker - GitHub] Using [[Undersampling Technique]]s and [[Logistic Regression (LR)]] in order to predict credit card fraud.
+
* [http://github.com/nickwalker037/Credit-Card-Fraud-Detection Credit Card Fraud Detection | Nick Walker - GitHub] Using [[Imbalanced Data#Under-sampling|Under-sampling]] techniques and [[Logistic Regression (LR)]] in order to predict credit card fraud.
 
* [http://www.kaggle.com/mlg-ulb/creditcardfraud Kernel for the Kaggle dataset "Credit Card Fraud Detection"]
 
* [http://www.kaggle.com/mlg-ulb/creditcardfraud Kernel for the Kaggle dataset "Credit Card Fraud Detection"]
  
−
Using [[Undersampling Technique]]s and [[Logistic Regression (LR)]] in order to predict credit card fraud
+
Using [[Imbalanced Data#Under-sampling|Under-sampling]] techniques and [[Logistic Regression (LR)]] in order to predict credit card fraud
  
 
This is the Kernel submission for the Kaggle competition "Credit Card Fraud Detection". The dataset contains 28 [[Principal Component Analysis (PCA)]] transformed features of transactions made by credit cards in September 2013 by European cardholders. The dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 total transactions (0.172% of total).
 
This is the Kernel submission for the Kaggle competition "Credit Card Fraud Detection". The dataset contains 28 [[Principal Component Analysis (PCA)]] transformed features of transactions made by credit cards in September 2013 by European cardholders. The dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 total transactions (0.172% of total).
  
−
Because of the highly unbalanced nature of the dataset, I used a [[Statistics for Intelligence#Confusion Matrix|Confusion Matrix]] to calculate the Precision and Recall of my results. I also used the [[Undersampling Technique]] in order to take a smaller amount of the normal transactions that occurred and train a logistic regressor based on this. I trained and applied the logistic regressor on all of the data, on only the undersampled data, and then I used the logistic regressor trained on the undersampled data and applied it to all of the data. My recall scores for each were as follows:
+
Because of the highly unbalanced nature of the dataset, I used a [[Statistics for Intelligence#Confusion Matrix|Confusion Matrix]] to calculate the Precision and Recall of my results. I also used the [[Imbalanced Data#Under-sampling|Under-sampling]] technique in order to take a smaller amount of the normal transactions that occurred and train a logistic regressor based on this. I trained and applied the logistic regressor on all of the data, on only the undersampled data, and then I used the logistic regressor trained on the undersampled data and applied it to all of the data. My recall scores for each were as follows:
  
 
* The logistic regressor trained on and applied to all of the data: 0.52  
 
* The logistic regressor trained on and applied to all of the data: 0.52  
Line 61: Line 61:
 
* The logistic regressor trained on the undersampled data and applied to all of the data: 0.92
 
* The logistic regressor trained on the undersampled data and applied to all of the data: 0.92
  
−
As you can see from my results above, the logistic regressor trained on the undersampled data and applied to all of the data had the best results, with a 92% recall rate. A fairly good start for applying the [[Undersampling Technique]] on only a logistic regressor.
+
As you can see from my results above, the logistic regressor trained on the undersampled data and applied to all of the data had the best results, with a 92% recall rate. A fairly good start for applying the [[Imbalanced Data#Under-sampling|Under-sampling]] technique on only a logistic regressor.

Revision as of 14:09, 2 September 2019

YouTube search... ...Google search


DharmaSecurity

I've built a Demo app called DharmaSecurity, a fraud detection tool for businesses. The way it works is that once signed up, a business will paste a code snippet into their website, and then they'll get access to a dashboard that tells them how many fraudulent accounts they have. Our app will use machine learning to automatically remove suspected fraud accounts, and flag likely ones for review. To build this, I use a suite of AWS tools, Python, Javascript, a Logistic Regression (LR) model, a credit card fraud dataset, and a library called OpenMined to enable federated learning and secure multi-party computation. I've packed a lot into this video, animations, code, music, screencasts, skits, etc. Enjoy! Code for "a Cybersecurity Startup" | Siraj Raval - GitHub

Credit Card Fraud Detection | Nick Walker

Using Under-sampling techniques and Logistic Regression (LR) in order to predict credit card fraud

This is the Kernel submission for the Kaggle competition "Credit Card Fraud Detection". The dataset contains 28 Principal Component Analysis (PCA) transformed features of transactions made by credit cards in September 2013 by European cardholders. The dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 total transactions (0.172% of total).

Because of the highly unbalanced nature of the dataset, I used a Confusion Matrix to calculate the Precision and Recall of my results. I also used the Under-sampling technique in order to take a smaller amount of the normal transactions that occurred and train a logistic regressor based on this. I trained and applied the logistic regressor on all of the data, on only the undersampled data, and then I used the logistic regressor trained on the undersampled data and applied it to all of the data. My recall scores for each were as follows:

  • The logistic regressor trained on and applied to all of the data: 0.52
  • The logistic regressor trained on and applied to only the undersampled data: 0.91
  • The logistic regressor trained on the undersampled data and applied to all of the data: 0.92

As you can see from my results above, the logistic regressor trained on the undersampled data and applied to all of the data had the best results, with a 92% recall rate. A fairly good start for applying the Under-sampling technique on only a logistic regressor.

Retrieved from "https://primo.ai/index.php?title=Watch_me_Build_a_Cybersecurity_Startup&oldid=10022"