Skip to content

Upgraded ONNXEmbeddings - Banking_Customer_Churn #1031

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chetan-hirapara wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Upgraded ONNXEmbeddings - Banking_Customer_Churn #1031

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
be3c28f
Upgraded ONNXEmbeddings
chetan-hirapara Nov 4, 2025
f7c8166
Merged step 1 and 2
chetan-hirapara Nov 4, 2025
ec861a3
increased records
chetan-hirapara Nov 12, 2025
c7915d9
Removed 00223C references. Added frame to graphic.
DallasBowden Nov 13, 2025
ce0d666
added introduction
chetan-hirapara Nov 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1,076 changes: 0 additions & 1,076 deletions UseCases/Banking_Customer_Churn_IVSM/IVSM_Banking_Customer_Churn.ipynb
View file
Open in desktop

This file was deleted.

508 changes: 0 additions & 508 deletions UseCases/Banking_Customer_Churn_IVSM/Step1.IVSM_Banking_Customer_Churn_Model_Install.ipynb
View file
Open in desktop

This file was deleted.

477 changes: 229 additions & 248 deletions ...ing_Customer_Churn_Embeddings_Setup.ipynb → ...g_Customer_Churn_Sentiment_Analysis.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

94 changes: 64 additions & 30 deletions ...M_Banking_Customer_Churn_embed_BYOM.ipynb → .../Step2_Train_Churn_Model_using_BYOM.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,19 +7,79 @@
"source": [
"<header>\n",
" <p style='font-size:36px;font-family:Arial; color:#F0F0F0; background-color: #00233c; padding-left: 20pt; padding-top: 20pt;padding-bottom: 10pt; padding-right: 20pt;'>\n",
" IVSM Banking Customer Churn Embed BYOM\n",
" Train and Export Banking Customer Churn Model using BYOM\n",
" <br>\n",
" <img id=\"teradata-logo\" src=\"https://storage.googleapis.com/clearscape_analytics_demo_data/DEMO_Logo/teradata.svg\" alt=\"Teradata\" style=\"width: 125px; height: auto; margin-top: 20pt;\">\n",
" </p>\n",
"</header>"
]
},
{
"cell_type": "markdown",
"id": "9fe96b47-414b-40de-a0d3-272246c72223",
"metadata": {},
"source": [
"<p style = 'font-size:20px;font-family:Arial'><b>Introduction</b></p>\n",
"\n",
"<center><img src=\"images/churn.webp\" style=\"border: 4px solid #404040; border-radius: 10px;\"/></center>\n",
"<p style = 'font-size:16px;font-family:Arial'>Source: <a href = 'https://medium.com/@islamhasabo/predicting-customer-churn-bc76f7760377'>Medium</a></p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>Customer churn is a critical metric in banking because it can directly impact a bank's revenue and profitability. When customers leave, banks lose the income they would have earned from those customers' transactions, investments, and account fees. Additionally, attracting new customers to replace those who have left can be expensive and time-consuming, so reducing customer churn is often more cost-effective than acquiring new customers.</p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>Customer churn can also be an indicator of customer satisfaction and loyalty. If customers leave at a high rate, they may be dissatisfied with the bank's products or services, customer service, or overall experience.</p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>Banks can use various strategies to reduce customer churns, such as improving customer service, offering more competitive rates and fees, providing personalized recommendations and offers, and enhancing digital channels and mobile apps. By tracking and analyzing customer churn rates, banks can identify areas for improvement and make strategic decisions to retain customers and improve overall customer satisfaction.</p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>In this demo, we demonstrate how to implement the entire lifecycle of churn prediction can using Vantage technologies and, specifically, the combination of Bring Your Own Model (BYOM), Vantage Analytics Library (VAL) and teradataml python client library solution.</p>\n",
"\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>Business Value of Customer Churn in Banking</strong>\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" Customer churn refers to the loss of clients who stop using a bank’s products or services. In the banking industry, churn has significant financial and strategic implications:\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>1. Revenue Loss:</strong> Each lost customer reduces recurring revenue from deposits, loans, credit cards, and investment products. High churn directly impacts profitability.\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>2. High Acquisition Costs:</strong> Acquiring a new customer is often <em>5–7 times more expensive</em> than retaining an existing one. Churn increases marketing and onboarding expenses.\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>3. Reduced Lifetime Value (CLV):</strong> Banks rely on long-term relationships to cross-sell products. Churn shortens customer lifecycles, reducing opportunities for upselling and cross-selling.\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>4. Brand Reputation & Trust:</strong> Frequent churn signals dissatisfaction, which can harm brand reputation and lead to negative word-of-mouth, further accelerating customer loss.\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>5. Regulatory & Competitive Pressure:</strong> In highly regulated markets, churn can indicate compliance or service gaps. Competitors can capitalize on these weaknesses, eroding market share.\n",
"</p>\n",
"<p style='font-size:16px;font-family:Arial'>\n",
" <strong>6. Predictive Insights for Growth:</strong> Understanding churn drivers helps banks improve customer experience, personalize offerings, and design retention strategies—turning risk into opportunity.\n",
"</p>\n",
"<p style = 'font-size:18px;font-family:Arial'><b>Why Vantage?</b></p>\n",
"<p style = 'font-size:16px;font-family:Arial'>The ML and AI industry continues to innovate at an unprecedented rate. Tools, technologies, and algorithms\t are being developed and improved in both the open source and commercial communities.</p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>Unfortunately, many of these techniques haven’t matured to the point where they are readily deployable to a stable, mature operational environment. Furthermore, many open-source techniques rely on fragile, manual enabling technologies.</p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>ClearScape Analytics <b>Bring Your Own Model</b> capabilities allow organizations to leverage third party and open-source models for scoring inside the Vantage Platform; providing enterprise-class scalability and operational stability for any number of users, applications, or volume of data.</p>\n",
"\n",
"<p style = 'font-size:18px;font-family:Arial'><b>Steps in the analysis:</b></p>\n",
"<ol style = 'font-size:16px;font-family:Arial'>\n",
" <li>Initiate a connection to Vantage</li>\n",
" <li>Data Transformation</li>\n",
" <li>Train-Test Split</li>\n",
" <li>Grant Access to ModelOps</li>\n",
" <li>Convert the model to PMML</li>\n",
" <li>Cleanup</li>\n",
"</ol>"
]
},
{
"cell_type": "markdown",
"id": "8c065558-5fb5-40fb-9893-a6c222cf3604",
"metadata": {},
"source": [
"<hr style=\"height:2px;border:none\">\n",
"## <hr style=\"height:2px;border:none\">\n",
"<p style = 'font-size:18px;font-family:Arial'><b>Import the required libraries</b></p>\n",
"\n",
"<p style = 'font-size:16px;font-family:Arial'>Here, we import the required libraries, set environment variables and environment paths (if required).</p>"
Expand All @@ -31,7 +91,7 @@
"metadata": {},
"source": [
"<div class=\"alert alert-block alert-warning\">\n",
"<p style = 'font-size:16px;font-family:Arial;color:#00233C'><b>Note: </b><i>Please ensure that <b>2.IVSM_Banking_Customer_Churn_Embeddings_Setup</b> is executed before running this file.</i></p>\n",
"<p style = 'font-size:16px;font-family:Arial;color:#00233C'><b>Note: </b><i>Please execute the Step1 notebooks before executing this notebook.</i></p>\n",
"</div>"
]
},
Expand Down Expand Up @@ -111,32 +171,6 @@
"%run -i ../run_procedure.py \"call get_data('DEMO_BankChurnIVSM_local');\""
]
},
{
"cell_type": "markdown",
"id": "7a44f6bc-d5e8-4e19-8625-e05342564ddc",
"metadata": {},
"source": [
"<p style = 'font-size:18px;font-family:Arial'><b>1.1 Confirmation for functions</b>\n",
"<p style = 'font-size:16px;font-family:Arial'>Confirm that the required functions are installed.</p>"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "46c8527e-a47e-461a-b44c-9fc748970d23",
"metadata": {},
"outputs": [],
"source": [
"from IPython.display import display, Markdown\n",
"\n",
"df_check= DataFrame.from_query('''select count(*) as cnt from dbc.tablesV where databasename = 'ivsm';''')\n",
"if df_check.get_values()[0][0] >= 10:\n",
" print('Functions are installed, please continue.')\n",
"else:\n",
" print('Functions are not installed, please go to Instalization notebook before proceeding further')\n",
" display(Markdown(\"[Initialization Notebook](./1.IVSM_Banking_Customer_Churn_Model_Install.ipynb)\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -716,7 +750,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.10"
"version": "3.11.14"
}
},
"nbformat": 4,
Expand Down
Loading