logo
  • Home
  • Blog-Navigation
  • Art
  • About
  • Contact

Author Archives: Roopam Upadhyay

Machine Learning for Debt Collection and Recovery Scorecards for Banks

· Roopam Upadhyay · 7 Comments

Covid-19 pandemic has ignited an unprecedented risk for the economy. Banks and financial institutions across the globe are expected to register unusually high default rates on loans once the moratorium and forbearance imposed by the governments and the regulators are lifted.  Scientific tools such as collection and recovery scorecards offer a mechanism to predict defaults

Read More…

Posted in Risk Analytics, Video Discussion |

How data science will shape post-COVID banking? – Video Discussion

· Roopam Upadhyay · Leave a comment

How data science will shape post-COVID banking? had a thought-provoking discussion with FrankBanker: 02:01 (Part 1) Impact on variables in Credit Models05:33 (Part 2) Are we going back to Judgemental Lending?07:50 (Part 3) Evaluating analytics readiness of Banks12:20 (Part 4) Is ‘IT’ the right place for Data Analytics?14:15 (Part 5) Changes in the Credit Scoring methodologies20:47

Read More…

Posted in Marketing Analytics |

Artificial Intelligence and Machine Learning for Business – A Video Talk

· Roopam Upadhyay · 1 Comment

How will artificial intelligence and machine learning transform businesses? In this introductory part of the talk, learn how artificial intelligence will play a pivotal role to resolve conflicts within businesses.

Read More...

Posted in Video Discussion |

Data Science Career – Q&A Session with Roopam

· Roopam Upadhyay · Leave a comment

This question and answer (Q&A) session will explore these topics: Identification of career opportunities in data science, machine learning, and Artificial Intelligence for beginners What to expect while starting your career in data science? How to make your career transition to data science, as an experienced professional, a smooth endeavor? What are the right strategies

Read More…

Posted in Video Discussion |

Convolutional Neural Networks (CNN) Simplified (Part 4)

· Roopam Upadhyay · 4 Comments

Welcome back to the deep learning example to build an OCR application. The idea of this simple application is to identify numbers in an image of written text. In the last part, we used three different models and got the following accuracy for identification of the test images: Model 1 – Logistic regression: 92% accuracy

Read More…

Posted in Deep Learning Neural Networks |

Deep Learning Models Simplified (Part 3)

· Roopam Upadhyay · 4 Comments

Facebook was a major sensation and a source of great amusement in a British country house in the early 20th century. It was such a big hit that it got a special mention in a newspaper published in the year 1902. Facebook, then, of course, had a completely different meaning than the online social media we

Read More…

Posted in Deep Learning Neural Networks |

Math of Deep Learning Neural Networks – Simplified (Part 2)

· Roopam Upadhyay · 6 Comments

Welcome back to this series of articles on deep learning and neural networks. In the last part, you learned how training a deep learning network is similar to a plumbing job. This time you will learn the math of deep learning. We will continue to use the plumbing analogy to simplify the seemingly complicated math. I

Read More…

Posted in Deep Learning Neural Networks |

Deep Learning and Neural Networks – Simplified (Part 1)

· Roopam Upadhyay · 16 Comments

The entire field of artificial intelligence, in the last few years, is built upon deep learning or deep neural networks. Notably, Apple’s Siri, Google-DeepMinds’ AlphaGo, or the self-driving mechanism in Tesla cars are all based on deep learning. Here, my goal is to make deep learning neural networks much more accessible for everyone. In this series

Read More…

Posted in Deep Learning Neural Networks |

Machine Learning : Cross Validation and Hyper-Parameter Tuning (Part 3)

· Roopam Upadhyay · 2 Comments

In the last part of this series on fundamental machine learning, you learned about regularization and cross-validation. Here, you will gain a sound understanding of model hyper-parameter tuning to develop robust models. The machines do learn but they still need a good human tutor. In the last part, you were also introduced to my paternal grandmother to

Read More…

Posted in Machine Learning and Artificial Intelligence, Regularization and Cross Validation |

Machine Learning : Regularization – Ridge, Lasso, & Elastic Net Simplified (Part 2)

· Roopam Upadhyay · 2 Comments

In the previous article, we started with the theme that overfitting is an inherent problem in machine learning associated with big data. Essentially, if you have many variables and their polynomial terms (X-variables) in a model you could fit any response data (y-variable) to perfection. This perfect fit for the observed data is overfitting since this model will

Read More…

Posted in Machine Learning and Artificial Intelligence, Regularization and Cross Validation |
Next Posts

Subscribe to Blog

Provide your email address to receive notifications of new posts

Must Read

Career in Data Science - Interview Preparation - Best Practices

Free Books - Machine Learning - Data Science - Artificial Intelligence

Case-Studies

- Marketing Campaign Management - Revenue Estimation & Optimization

Customer Segmentation - Cluster Analysis - Segment wise Business Strategy

- Risk Management - Credit Scorecards

- Sales Forecasting - Time Series Models

Credit

I must thank my wife, Swati Patankar, for being the editor of this blog.

Pages

  • Blog-Navigation
  • Art
  • About
  • Contact
© Roopam Upadhyay
  • Blog-Navigation
  • Art
  • About
  • Contact
 

Loading Comments...