client2vec: Towards Systematic Baselines for Banking Applications

Baldassini, Leonardo; Serrano, Jose A. Rodriguez

doi:10.48550/arxiv.1802.04198

Cited by 2 publications

(2 citation statements)

References 21 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Towards that end, they also use an n-skip-gram model to learn customer embeddings and track its evolution over time as purchases are made. [20] uses a stacked denoising autoencoder to learn customer embeddings for improving their campaign decisions or clustering clients into classes.…”

Section: Background and Related Work A Transaction-based Item And Cus...mentioning

confidence: 99%

Generating Realistic Sequences of Customer-Level Transactions for Retail Datasets

Doan

Veira

Keng

2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

In order to better engage with customers, retailers rely on extensive customer and product databases which allows them to better understand customer behaviour and purchasing patterns. This has long been a challenging task as customer modelling is a multi-faceted, noisy and time-dependent problem. The most common way to tackle this problem is indirectly through task-specific supervised learning prediction problems, with relatively little literature on modelling a customer by directly simulating their future transactions. In this paper we propose a method for generating realistic sequences of baskets that a given customer is likely to purchase over a period of time. Customer embedding representations are learned using a Recurrent Neural Network (RNN) which takes into account the entire sequence of transaction data. Given the customer state at a specific point in time, a Generative Adversarial Network (GAN) is trained to generate a plausible basket of products for the following week. The newly generated basket is then fed back into the RNN to update the customer's state. The GAN is thus used in tandem with the RNN module in a pipeline alternating between basket generation and customer state updating steps. This allows for sampling over a distribution of a customer's future sequence of baskets, which then can be used to gain insight into how to service the customer more effectively. The methodology is empirically shown to produce baskets that appear similar to real baskets and enjoy many common properties, including frequencies of different product types, brands, and prices. Furthermore, the generated data is able to replicate most of the strongest sequential patterns that exist between product types in the real data.

show abstract

Section: Background and Related Work A Transaction-based Item And Cus...mentioning

confidence: 99%

Generating Realistic Sequences of Customer-Level Transactions for Retail Datasets

Doan

Veira

Keng

2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

show abstract

“…From the very first day following their release, approaches like word2vec or Glove [20,21,22,23] that yield dense representations for state sequences, have significantly emphasized the value of pre-trained representations of discrete sequential data for downstream tasks [24,25]. Since then those found application not only in language modeling [26,27,28,29] but also in biology [30,31], graph analysis [32,33] and even banking [34]. Similar approaches have received an overwhelming attention and became part of the respective state-of-the-art approaches.…”

Section: Introductionmentioning

confidence: 99%

DenseHMM: Learning Hidden Markov Models by Learning Dense Representations

Sicking¹,

Pintz²,

Akila³

et al. 2020

Preprint

View full text Add to dashboard Cite

We propose DenseHMM -a modification of Hidden Markov Models (HMMs) that allows to learn dense representations of both the hidden states and the observables. Compared to the standard HMM, transition probabilities are not atomic but composed of these representations via kernelization. Our approach enables constraint-free and gradient-based optimization. We propose two optimization schemes that make use of this: a modification of the Baum-Welch algorithm and a direct co-occurrence optimization. The latter one is highly scalable and comes empirically without loss of performance compared to standard HMMs. We show that the non-linearity of the kernelization is crucial for the expressiveness of the representations. The properties of the DenseHMM like learned co-occurrences and log-likelihoods are studied empirically on synthetic and biomedical datasets.

show abstract

client2vec: Towards Systematic Baselines for Banking Applications

Cited by 2 publications

References 21 publications

Generating Realistic Sequences of Customer-Level Transactions for Retail Datasets

Generating Realistic Sequences of Customer-Level Transactions for Retail Datasets

DenseHMM: Learning Hidden Markov Models by Learning Dense Representations

Contact Info

Product

Resources

About