Skip to content

Home

Jump to bottom
smruthi33 edited this page Sep 8, 2018 · 18 revisions

Welcome to the Banking Risk Mitigation wiki!

Umbrella SI Journey

Leverage IBM Cloud, Watson services and Open source technologies to analyze client information and get an early warning prior to any client investment.

Short Name

Client Network Banking

Short Description

Knowing your Client is an essential best practice because it is the foundation for all succeeding steps in the credit risk management process. To be successful, you must operate on pertinent, accurate, and timely information. However, Client network information is scattered across various sources. This pattern provides real-time information regarding a client, known as a client-network, all collated in a single place. It is targeted at Relationship managers at Banks who handle customer investments.

Offering Type

Artificial Intelligence

Introduction

Relationship managers at banks handle client investments. One of the most important considerations in investing client money for a financial advisor is trying to assess the client’s risk due to certain changes in their environment. Further, investments are affected by happenings in the ecosystem or client network with events such as Management Change, Management Default, Share Price Deviations, Credit Rating, Strike, and more.

This code pattern takes real-time information from popular news sites, extracts the clients affected by it with the help of Watson Natural Language Understanding. This is achieved with the help of the following code patterns:

Finally, a flask application connects the algorithm to a UI which can be used by a user to prune down to the required information. Thus, helping the relationship manager to understand the current client-network and provide the right advice to the investor.

What makes this Code Pattern valuable:

  • Client network information is scattered across various sources.
  • Our solution provides real-time information on the client network collated as a knowledge graph at a single place.
  • The solution is built to make a customer relationship manager's job easier, in order to take an informed decision in customer investments.

Author

By Vishal Chahal, Smruthi Raj Mohan

Code

https://github.com/IBM/banking-risk-mitigation-nlu-studio

Demo

N/A

Video

https://youtu.be/B_NDyeqEn2k

Overview

This pattern provides real-time information regarding a client, known as a client-network, all collated in a single place. This information is in compliance with the most important events impacting any organization. It takes real-time information from popular news sites, extracts the clients affected by it with the help of Watson Natural Language Understanding. The application demonstrates a methodology to derive insights about customer insights with IBM Cloud, Watson services, Python Flask and Python NLTK.

Flow

  1. The user interacts with the app UI to request relevant information corresponding to an event or a client.
  2. The web app UI interacts with the Python-Flask server to receive the required information from the appropriate API.
  3. The flask APIs scrape real-time news from popular online news portals.
  4. The scraped data is sent to NLU Studio to extract important entities.
  5. A configuration JSON file is sent into the flask app, to further prune on the results obtained on NLU.
  6. Finally, all the collected information is pushed back into the interactive UI.

Included components

  • Watson Natural Language Understanding: An IBM Cloud service that can analyze text to extract meta-data from content such as concepts, entities, keywords, categories, sentiment, emotion, relations, semantic roles, using natural language understanding.
  • Python Runtime: IBM Cloud powers a python runtime by the python_buildpack. The python_buildpack provides a complete runtime environment for both Python 2 and Python 3 apps.

Featured technologies

  • Natural Language Processing: Natural Language Processing is a field that covers computer understanding and manipulation of human language, and it’s ripe with possibilities for newsgathering.
  • Cloud: Accessing computer and information technology resources through the Internet.
  • Python: Python is a programming language that lets you work more quickly and integrate your systems more effectively.
  • Artificial Intelligence: Artificial intelligence is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals.

Blog

Relationship managers at banks handle customer investments. For a relationship manager, knowing a Client's current situation or scenario is required to decide whether or not to invest in a client. To be successful in taking the right decision, you must operate on pertinent, accurate, and timely information.

What if we can build a tool that can help you gather all the required information about your clients. To help you make an informed decision on whether or not to invest in a client?

This pattern provides real-time information regarding a client, known as a client-network, all collated in a single place. This information is in compliance with the most important events impacting any organization. The following are the event triggers in the built application:

  • Management Change
  • Management Default
  • Credit Rating
  • Strike
  • Share Price Deviation

Find out more in the Code Pattern Repo!

Links

Clone this wiki locally