The finance industry is constantly faced with an ever evolving set of challenges including credit card fraud, identity theft, network intrusion, money laundering, human trafficking, and illegal sales of firearms. There is also the newly emerging threat of fake news in financial media that can lead to distortions in trading strategies and investment decisions. In addition, traditional problems such as customer analytics, forecasting, and recommendations take on a unique flavor when applied to financial data. A number of new ideas are emerging to tackle all these problems including semi-supervised learning methods, deep learning algorithms, network/graph based solutions as well as linguistic approaches. These methods must often be able to work in real-time and be able handle large volumes of data. The purpose of this workshop is to bring together researchers and practitioners to discuss both the problems faced by the financial industry and potential solutions. This will be the third of a sequence of finance related workshops we have organized at KDD. The first workshop was held at KDD 2017 and the second workshop at KDD 2019. Based on popular request, we have decided to expand the scope from anomaly detection to a broader area of finance.
We invite papers on machine learning and AI with applications to the financial industry. Topics of interest include, but are not limited to, the following:
Analysis of financial graphs
Early detection of emerging phenomena
Fraud, anti money laundering and identity theft
Fake news in financial outlets
Fairness in lending
Enhanced risk modeling
Monitoring
Recommendations
Text analytics of financial reports, forecasts and documents
Forecasting
Social media mining
Manipulation in cryptocurrency markets
● Analysis of financial graphs:
Node embeddings for downstream classification and prediction
Link prediction for forecasting
Node classification on partial graphs
Analysis of heterogeneous graphs
● Semi-supervised anomaly detection (aka Novelty Detection):
Data available for training does not contain any anomalies and represents expected operation of the system.
Data with “positive only” labels.
● Explainable models:
Models that can explain their decisions in interpretable ways
Post-hoc methods that can be used to explain outputs of other detection algorithms
● Human-in-the-loop techniques for anti money laundering and other financial crimes:
Interactive ranking techniques
Methods that can handle exploration-exploitation trade-off
Novel human feedback gathering strategies beyond labeling
● Adversarially-robust detection:
Methods that are provably robust to evasion and camouflage
Evasion-cost aware fraud and intrusion detection
Analysis of evasion schemes and camouflage mechanisms
● Time Series:
Predictions in temporal graphs
Forecasting
● Text Analytics and NLP:
Transfer learning for financial text data
Detection of emerging trends
Linguistic approaches for fake news detection
Analysis of unstructured text data within transactional financial data.
Overview of Industry Challenges
Short papers from financial industry practitioners that introduce domain specific problems and challenges to academic researchers. These papers should describe problems that can inspire new research directions in academia, and should serve to bridge the information gap between academia and the financial industry.
Algorithmic Tutorials
Short tutorials from academic researchers that explain current solutions to challenges related to the technical areas mentioned above, not necessarily limited to the financial domain. These tutorials will serve as an introduction and enable financial industry practitioners to employ/adapt latest academic research to their use-cases.
All submissions must be PDFs formatted in the Standard ACM Conference Proceedings Template. Submissions are limited to 8 content pages or less, including all figures and tables but excluding references. Due to popular request from industry practitioners, we are also accepting 1-page to 2-page summaries or extended abstracts. All accepted papers will be presented as posters and some would be selected for oral presentations, depending on schedule constraints. Accepted papers will be posted on the workshop website.
Authors should clearly indicate in their abstracts the kinds of submissions that the papers belong to, to help reviewers better understand their contributions.
Reviews are single blind. Please include author names and affiliations in your submission.
Papers (full papers or 1-2 page summaries) should be submitted on CMT3 by May 20, 2020 11:59 PM Pacific Time
https://cmt3.research.microsoft.com/MLF2020.
Submission deadline: May 20, 2020 11:59 PM Pacific Time at https://cmt3.research.microsoft.com/MLF2020.
New Submission deadline: June 7, 2020 11:59 PM Pacific Time at https://cmt3.research.microsoft.com/MLF2020.
Author notification: June 15, 2020 June 30, 2020 July 3, 2020
Workshop: August 24, 2020
ACM SIGKDD and the KDD 2020 organization committee are monitoring the COVID-19 situation closely and investigating various feasible options. Latest update can be found at https://www.kdd.org/kdd2020/.