Comments for Jupyter notebooks – a Swiss Army Knife for Quants

Comment on CVA Calculation with QuantLib and Python by _bn_ln

_bn_ln — Sat, 17 Nov 2018 22:11:33 +0000

In reply to _bn_ln.

ignore my comment, it’s clearly all paths

Comment on CVA Calculation with QuantLib and Python by _bn_ln

_bn_ln — Sat, 17 Nov 2018 21:35:54 +0000

Great blog, it’s very useful as a reference. Just one question though, isn’t the calculated EE = np.sum(E, axis=0)/N too low? Shouldn’t the sum by divided by number of paths with exposure > 0, rather than all paths?

LikeLike

Comment on Fooling Around with KNIME cont’d: Deep Learning by Signature Verification with deep learning / transfer learning using Keras and KNIME | Jupyter notebooks – a Swiss Army Knife for Quants

Sun, 26 Aug 2018 05:31:01 +0000

[…] the previous posts we used traditional Machine Learning methods and Deep Learning in Python and KNIME to detect credit card fraud, in this post we will see how to use a pretrained deep neural networks […]

LikeLike

Comment on From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part III by Signature Verification with deep learning / transfer learning using Keras and KNIME | Jupyter notebooks – a Swiss Army Knife for Quants

Sun, 26 Aug 2018 05:30:59 +0000

[…] the previous posts we used traditional Machine Learning methods and Deep Learning in Python and KNIME to detect credit card fraud, in this post we will see how to use a pretrained […]

LikeLike

Comment on From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part I by Signature Verification with deep learning / transfer learning using Keras and KNIME | Jupyter notebooks – a Swiss Army Knife for Quants

Sun, 26 Aug 2018 05:30:56 +0000

[…] the previous posts we used traditional Machine Learning methods and Deep Learning in Python and KNIME to detect credit card fraud, in this post we will see how […]

LikeLike

Comment on From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part III by Fooling Around with KNIME cont’d: Deep Learning | Jupyter notebooks – a Swiss Army Knife for Quants

Sun, 05 Aug 2018 03:41:45 +0000

[…] frameworks TensorFlow and Keras. So I thought lets revisited our deep learning model for the fraud detection and try to implement in KNIME using […]

LikeLike

Comment on Fooling around with KNIME by Fooling Around with KNIME cont’d: Deep Learning | Jupyter notebooks – a Swiss Army Knife for Quants

Sun, 05 Aug 2018 03:41:42 +0000

[…] my previous post I wrote about my first experiences with KNIME and we implemented three classical supervised machine […]

LikeLike

Comment on From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part I by Fooling around with KNIME | Jupyter notebooks – a Swiss Army Knife for Quants

Thu, 19 Jul 2018 16:08:26 +0000

[…] to give it a try and I migrated my logistic regression fraud detection sample from my previous blog posts into a graphical […]

LikeLike

Comment on From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part I by From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part III | Jupyter notebooks – a Swiss Army Knife for Quants

Wed, 20 Jun 2018 00:50:32 +0000

[…] will continue to use the same data apply the same transformation which we are using since the first part of this […]

LikeLike

Comment on From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part II by From Logistic Regression in SciKit-Learn to Deep Learning with TensorFlow – A fraud detection case study – Part III | Jupyter notebooks – a Swiss Army Knife for Quants

Wed, 20 Jun 2018 00:50:29 +0000

[…] to learn a delta hedge) I will come back to our credit card fraud detection case. In the previous part we have build a logistic regression classifier in TensorFlow to detect fraudulent transactions. We […]

LikeLike