NMTucker: Non-linear Matryoshka Tucker Decomposition for Financial Time Series Imputation

Uras Varolgunes, Dan Zhou, Dantong Yu, Ajim Uddin

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Missing values in financial time series data are of paramount importance in financial modeling and analysis. Appropriately handling missing data is essential to ensure the accuracy and reliability of financial models and forecasts. In this paper, we focus on datasets containing multiple attributes of different firms across time, such as firm fundamentals or characteristics, which can be represented as three dimensional tensors with the dimensions time, firm and attribute. Hence, the task of imputing missing values for these datasets can also be formulated as a tensor completion problem. Tensor completion has a wide range of applications, including link prediction, recommendation, and scientific data extrapolation. The widely used completion algorithms, CP and Tucker decompositions, factorize an N-order tensor into N embedding matrices and use multi-linearity among the factors to reconstruct the tensor. Real-world data are often highly sparse and involve complex interactions beyond simple N-order linearity; they demand models capable of capturing latent variables and their non-linear multi-way interactions. We design an algorithm, called Non-Linear Matryoshka Tucker Completion (NMTucker), that uses element-wise Tucker decomposition, multi-layer perceptrons, and non-linear activation functions to solve these challenges and ensure its scalability. To avoid the overfitting problem with existing neural network-based tensor algorithms, we develop a novel strategy that recursively decomposes a tucker core into smaller ones, reduces the number of trainable parameters, and regularizes the complexity. Its structure is similar to Matryoshka dolls of decreasing size in which one is nested inside another. We conduct experiments to show that NMTucker effectively mitigates overfitting and demonstrate its superior generalization capability (up to 53.91% less RMSE) in comparison with the state-of-the-art models in multiple tensor completion tasks.

Original languageEnglish (US)
Title of host publicationICAIF 2023 - 4th ACM International Conference on AI in Finance
PublisherAssociation for Computing Machinery, Inc
Number of pages8
ISBN (Electronic)9798400702402
StatePublished - Nov 27 2023
Event4th ACM International Conference on AI in Finance, ICAIF 2023 - New York City, United States
Duration: Nov 27 2023Nov 29 2023

Publication series

NameICAIF 2023 - 4th ACM International Conference on AI in Finance


Conference4th ACM International Conference on AI in Finance, ICAIF 2023
Country/TerritoryUnited States
CityNew York City

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Finance


  • Data Imputation
  • Financial Time Series
  • Non-linear Tensor Decomposition
  • Sparse Tensor Completion


Dive into the research topics of 'NMTucker: Non-linear Matryoshka Tucker Decomposition for Financial Time Series Imputation'. Together they form a unique fingerprint.

Cite this