# Dynamic Customer Embeddings for Financial Service Applications

arXiv: https://arxiv.org/abs/2106.11880 · HTML: https://mlsanity.com/paper/2106.11880/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 20 of 20)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [A Survey on Session-based Recommender Systems](https://mlsanity.com/paper/1902.04864/) (2019)
- [Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data](https://mlsanity.com/paper/2012.15330/) (2020)
- [Deep Coevolutionary Network: Embedding User and Item Features for Recommendation](https://mlsanity.com/paper/1609.03675/) (2016)
- [MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention](https://mlsanity.com/paper/2009.14799/) (2020)
- [Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps](https://mlsanity.com/paper/2006.06427/) (2020)
- [Interleaved Sequence RNNs for Fraud Detection](https://mlsanity.com/paper/2002.05988/) (2020)
- [Customer Lifetime Value Prediction Using Embeddings](https://mlsanity.com/paper/1703.02596/) (2017)
- [Characterizing and Forecasting User Engagement with In-app Action Graph: A Case Study of Snapchat](https://mlsanity.com/paper/1906.00355/) (2019)
- [DeepTrax: Embedding Graphs of Financial Transactions](https://mlsanity.com/paper/1907.07225/) (2019)
- [Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks](https://mlsanity.com/paper/1706.07684/) (2017)
- [I Know You'll Be Back: Interpretable New User Clustering and Churn Prediction on a Mobile Social Application](https://mlsanity.com/paper/1910.01447/) (2019)
- [Multimodal Fusion Refiner Networks](https://mlsanity.com/paper/2104.03435/) (2021)
- [Dynamic Embeddings for Interaction Prediction](https://mlsanity.com/paper/2011.05208/) (2020)
- [client2vec: Towards Systematic Baselines for Banking Applications](https://mlsanity.com/paper/1802.04198/) (2018)
- [IACN: Influence-aware and Attention-based Co-evolutionary Network for Recommendation](https://mlsanity.com/paper/2103.02866/) (2021)
- [Learning Student Interest Trajectory for MOOCThread Recommendation](https://mlsanity.com/paper/2101.05625/) (2021)

## Built on by (most cited first, 3 of 3)

- [FinTRec: Transformer Based Unified Contextual Ads Targeting and Personalization for Financial Applications](https://mlsanity.com/paper/2511.14865/) (2025)
- [Autoencoder-based General Purpose Representation Learning for Customer Embedding](https://mlsanity.com/paper/2402.18164/) (2024)
- [DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation](https://mlsanity.com/paper/2609.32215/) (2026)

## Abstract (arXiv)

As financial services (FS) companies have experienced drastic technology driven changes, the availability of new data streams provides the opportunity for more comprehensive customer understanding. We propose Dynamic Customer Embeddings (DCE), a framework that leverages customers' digital activity and a wide range of financial context to learn dense representations of customers in the FS industry. Our method examines customer actions and pageviews within a mobile or web digital session, the sequencing of the sessions themselves, and snapshots of common financial features across our organization at the time of login. We test our customer embeddings using real world data in three prediction problems: 1) the intent of a customer in their next digital session, 2) the probability of a customer calling the call centers after a session, and 3) the probability of a digital session to be fraudulent. DCE showed performance lift in all three downstream problems.