caspr
CASPR is a deep learning framework applying transformer architecture to learn and predict from tabular data at scale.
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.6%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
CASPR is a deep learning framework applying transformer architecture to learn and predict from tabular data at scale.
Basic Info
Statistics
- Stars: 38
- Watchers: 7
- Forks: 3
- Open Issues: 3
- Releases: 0
Topics
Metadata Files
README.md
CASPR is a transformer-based framework for deep learning from sequential data in tabular format, most common in business applications.
Tasks critical to enterprise profitability, such as customer churn prediction, fraudulent account detection or customer lifetime value estimation, are often tackled by models trained on features engineered from customer data in tabular format. Application-specific feature engineering however adds development, operationalization and maintenance costs over time. Recent advances in representation learning present an opportunity to simplify and generalize feature engineering across applications. With **CASPR** we propose a novel approach to encode sequential data in tabular format (e.g., customer transactions, purchase history and other interactions) into a generic representation of a subject's (e.g., customer's) association with the business. We evaluate these embeddings as features to train multiple models spanning a variety of applications (see: [paper](https://arxiv.org/abs/2211.09174)). CASPR, Customer Activity Sequence-based Prediction and Representation, applies transformer architecture to encode activity sequences to improve model performance and avoid bespoke feature engineering across applications. Our experiments at scale validate CASPR for both small and large enterprise applications.
Getting Started & Resources
CASPR: Customer Activity Sequence-based Prediction and Representation (NeurIPS 2022, New Orleans: Tabular Representation Learning)
Build
- pre-requisites:
python==3.9, setuptools - building the wheel:
python setup.py build bdist_wheel
- pre-requisites:
Installation
```
(now)
pip install .\dist\AI.Models.CASPR-
(future)
pip install AI.Models.CASPR[
use any of below modifiers, to customize the installation for target system / usecase:
horovod - for distributed training and inference on Horovod
databricks - for distributed training and inference on Databricks
aml - for (distributed) training and inference on Azure ML
hdi - for execution on Azure HD Insights
xai - to enable explainability
test - for extended test execution
dev - for development purposes only
* Examples
(TODO: can we point to a well commented one of our examples w/ or w/o data?)
Contributions and Feedback
We welcome contributions! Please see the contribution guidelines.
For feature requests or bug reports please file a GitHub Issue.
Code of Conduct
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
License
This project is licensed under the MIT License.
Owner
- Name: Microsoft
- Login: microsoft
- Kind: organization
- Email: opensource@microsoft.com
- Location: Redmond, WA
- Website: https://opensource.microsoft.com
- Twitter: OpenAtMicrosoft
- Repositories: 7,257
- Profile: https://github.com/microsoft
Open source projects and samples from Microsoft
Citation (CITATION.cff)
cff-version: 1.2.0
title: CASPR
message: "Please use this information to cite CASPR in
research or other publications."
authors:
- given-names: Pin-Jung
family-names: Chen
email: pinjung.chen@microsoft.com
affiliation: Microsoft Corporation
- given-names: Sahil
family-names: Bhatnagar
email: sahil.bhatnagar@microsoft.com
affiliation: Microsoft Corporation
- given-names: Damian Konrad
family-names: Kowalczyk
email: damian.kowalczyk@microsoft.com
affiliation: Microsoft Corporation
- given-names: Mayank
family-names: Shrivastava
email: mayank.shrivastava@microsoft.com
affiliation: Microsoft Corporation
- given-names: Sagar
family-names: Goyal
email: goyalsagar@outlook.com
date-released: 2022-11-16
repository-code: "https://github.com/microsoft/CASPR"
license: "MIT"
keywords:
- deep learning
- machine learning
- tabular data
version: 0.2.6
doi: 10.48550/arXiv.2211.09174
references:
- type: article
authors:
- given-names: Pin-Jung
family-names: Chen
email: pinjung.chen@microsoft.com
affiliation: Microsoft Corporation
- given-names: Sahil
family-names: Bhatnagar
email: sahil.bhatnagar@microsoft.com
affiliation: Microsoft Corporation
- given-names: Damian Konrad
family-names: Kowalczyk
email: damian.kowalczyk@microsoft.com
affiliation: Microsoft Corporation
- given-names: Mayank
family-names: Shrivastava
email: mayank.shrivastava@microsoft.com
affiliation: Microsoft Corporation
- given-names: Sagar
family-names: Goyal
email: goyalsagar@outlook.com
title: "CASPR: Customer Activity Sequence-based Prediction and Representation"
year: 2022
journal: ArXiv
doi: 10.48550/arXiv.2211.09174
url: https://arxiv.org/abs/2211.09174
abstract: >-
Tasks critical to enterprise profitability, such as customer churn prediction, fraudulent account detection or customer lifetime value estimation, are often tackled by models trained on features engineered from customer data in tabular format. Application-specific feature engineering adds development, operationalization and maintenance costs over time. Recent advances in representation learning present an opportunity to simplify and generalize feature engineering across applications. When applying these advancements to tabular data researchers deal with data heterogeneity, variations in customer engagement history or the sheer volume of enterprise datasets. In this paper, we propose a novel approach to encode tabular data containing customer transactions, purchase history and other interactions into a generic representation of a customer's association with the business. We then evaluate these embeddings as features to train multiple models spanning a variety of applications. CASPR, Customer Activity Sequence-based Prediction and Representation, applies Transformer architecture to encode activity sequences to improve model performance and avoid bespoke feature engineering across applications. Our experiments at scale validate CASPR for both small and large enterprise applications.
GitHub Events
Total
Last Year
Committers
Last synced: over 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Microsoft Open Source | m****e | 5 |
| Sahil Bhatnagar | s****2@g****m | 3 |
| Damian Kowalczyk | n****k | 3 |
| Damian Kowalczyk | d****c@m****m | 1 |
| sabhatn | s****n@m****m | 1 |
| microsoft-github-operations[bot] | 5****] | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 11 months ago
All Time
- Total issues: 3
- Total pull requests: 3
- Average time to close issues: N/A
- Average time to close pull requests: about 7 hours
- Total issue authors: 3
- Total pull request authors: 2
- Average comments per issue: 0.0
- Average comments per pull request: 1.0
- Merged pull requests: 3
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- zhouzhongmi (1)
- rjr89 (1)
- ananv21 (1)
Pull Request Authors
- nightflight-dk (2)
- cruck12 (1)