schedule Aug 7th 11:45 AM - 01:15 PM place Neptune people 31 Interested

Financial Scorecards are used widely in all financial organizations for different kinds of ratings. This workshop will take you through the building and validation process of a financial scorecard using data.Financial Scorecards are used by banking organizations to judge the financial stability of their portfolio and take business decisions. These scorecards help in tracking and collections.

This workshop is designed for audience to take them through the process of developing a scorecard using Python. The workshop will guide you through the EDA process using Python . We would cover basics of EDA and how python visualizations can support us in data mining. We aim to cover step by step process of building a scorecard and Use of different Machine Learning algorithms to build a better scorecard by comparing the outputs of different algorithms. We will demonstrate 3 different Machine learning algorithms Random Forest , Support Vector Machine and Gradient Boosting and their outcomes while building this scorecard.

Along the workshop we would introduce you to Python libraries that can be used to build these scorecards with more efficacy.

The key python libraries that we will be using will be Pandas , Numpy ,Scipy , Matplotlib and seaborn. We would demonstrate functions of these libraries used in building scorecards.

This will be a hands on session and attendees can come with their laptops for better understanding and follow up of session.

 
 

Outline/Structure of the Workshop

Introduction to application of Financial Scorecard. What business problem does it solve ( 8-10 mins)

Exploratory Data Analysis - Data Wrangling using Python ( 18- 20 mins)

Intro to ML and Supervised Learning ( 4- 5 mins)

Understanding Random Forest ( 4-5 mins)

Building the scorecard using Machine Learning algorithms - Random Forest Walk through in Python (15 -20 mins)

Exercise with class on Implementing Gradient Boosting ( 10 mins)

Comparing Scorecards and selecting the best ( 5 mins)

Scorecard Validation ( 5 mins)

Q & A ( 10 mins)

Learning Outcome

Data wrangling and mining using Python

Building Supervised Machine Learning algorithms with algorithm understanding - Random Forest and Gradient Boosting

Compare the outputs of different algorithms.

Work with key Python libraries used for Data Analysis & Machine Learning

Understand the mathematics behind creating a perfect Financial Scorecard

Understanding of concepts like Binning , Variable Selection , IV (Information Value) , Weight of Evidence(WoE )

Target Audience

Machine Learning Practitioners , Aspirational Data Scientists , Data Science Enthusiast, Python Programmers , Financial Experts , Banking Professionals

Prerequisites for Attendees

Basic Knowledge of Data Science and Python.

For tools, we will be using Google Colab Jupyter notebooks with source code hosted on Github.

Alternatively, Anaconda python Distribution (Jupyter Notebooks) can also be used on local machine based on preference.

Anaconda Installation Instructions. Please install ahead of the workshop since this will not be covered during the workshop. Visit https://www.anaconda.com/distribution/#download-section ; Download the latest 3.x version.

Here is the github link for Data and Python file.

https://github.com/kavitablockyto/ScorecardODSC

Github and google account credentials would be needed to access and save files during the workshop

Libraries used:

  • Numpy
  • Pandas
  • Matplotlib
  • seaborn
  • Sklearn
schedule Submitted 7 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Abirami Venkatachalam
    By Abirami Venkatachalam  ~  3 months ago
    reply Reply

    Hi Kavitha /Nirav,

    1. Will you be discussing about creating similar dashboards/scorecard  for
      • Winning opportunities/projects for AEC industry?
      • Managing projects in these type of industries?
    2. How about HR related scorecards?

    Regards, Abirami

    • Kavita Dwivedi
      By Kavita Dwivedi  ~  3 months ago
      reply Reply

      Hi Abirami ,

      This session focusses on Financial Scorecards used for Banking Industry. We will not be touching upon AEC industry /Winning Opportunities in these industries or HR related Scorecards.

      Having said that , the process of building a scorecard would be 70-80% similar across industries as it is in one way rank ordering of objects based on your input data set and your outcome variable( In Banking default/non default and in AEC won /Not won). As this is a technical session , it will be help you to understand the process of Scorecard Building and then with minor changes migrate it to other industries.

      Hope this helps

      Kavita

       

       

  • Prashanth Chandra Shekhar
    By Prashanth Chandra Shekhar  ~  3 months ago
    reply Reply

    Hi Kavitha / Nirav,

    Looking forward to the session.

    Just wanted to know on why is it called scorecard and not as dashboard?

    And why is there no mention of libraries like sklearn?

    Thanks

    • Kavita Dwivedi
      By Kavita Dwivedi  ~  3 months ago
      reply Reply

      Hi Prashanth ,

       

      This session focusses on building a Credit Scorecard . These are not just dashboards , but the scoreacards will be built using modeling techniques and the session will focus on how to get your most accurate scorecard. In Banking nomenclature , these are called scorecards because they are used to measure the credit worthiness of an individual.This is like allotting a score post analysis of all his demographic , behaviour and bureau variables.

      The libraries mentioned are few indicative ones only.

      Regards,

      Kavita

       

       

  • Naresh Jain
    By Naresh Jain  ~  4 months ago
    reply Reply

    Hi Kavita, Nirav,

    Can you please help me understand, while creating a scorecard, what specific problem are you trying to solve using ML?

    • Kavita Dwivedi
      By Kavita Dwivedi  ~  4 months ago
      reply Reply

      Hi Naresh ,

      Thanks for reviewing the proposal. In this talk we would be discussing the creation of a scorecard to measure the credit worthiness of a customer.based on his application and behaviour data of his all banking products. This will help us measure the riskiness of the customer and also on aggregation will help in loss forecasting of a portfolio. These scorecards can be used during entire life cycle of a customer right from application , behaviour and collection portfolios. These scorecards help banks take decision whether to accept an application , restructure a loan or go for early collections etc.

       

      Rgds,

      Kavita

       

  • Usha Rengaraju
    By Usha Rengaraju  ~  5 months ago
    reply Reply

    Kavita and Nirav,

    Kindly mention the python libraries which will be covered in the workshop . Does your workshop require prior programming experience ?

    Thanks and Regards,

    Usha Rengaraju

     

    • Kavita Dwivedi
      By Kavita Dwivedi  ~  5 months ago
      reply Reply

      Thanks Usha for your thoughts. We have updated the proposal with required details on python libraries. Basic Python /Programming experience is good to have, but our tutorial will start from the initial step so even someone new will be able to pick it up.

      Regards,

      Kavita

  • Dr. Vikas Agrawal
    By Dr. Vikas Agrawal  ~  5 months ago
    reply Reply

    Dear Nirav: Please add in the description that this will be a hands-on tutorial/workshop, and please mention the algorithms and libraries you plan to use. Perhaps information on what needs to be installed by attendees will be good to have as well. Warm Regards, Vikas

    • Kavita Dwivedi
      By Kavita Dwivedi  ~  5 months ago
      reply Reply

      Thanks Dr. Vikas for your time to review the proposal and give valuable suggestions. We have updated the proposal with required details. 

      Regards,

      Kavita

  • Ashay Tamhane
    By Ashay Tamhane  ~  5 months ago
    reply Reply

    Thanks for the proposal. Could you kindly elaborate on which ML algorithms will be demonstrated?

    • Kavita Dwivedi
      By Kavita Dwivedi  ~  5 months ago
      reply Reply

      Hi Ashay,

       

      Thanks for reviewing the proposal . We are largely looking at discussing Random Forest , Gradient Boosting and Support Vector Machines.

       

      Regards,

      Kavita

  • Anoop Kulkarni
    By Anoop Kulkarni  ~  7 months ago
    reply Reply

    Thanks for your proposal. This is a great area to be working on and looking forward to your talk. I have no specific questions at this time, your description is fairly clear. Thank you!

     

    ~anoop