Nonlinear Tensor Completion Using Domain Knowledge: An Application in Analysts' Earnings Forecast
Document Type
Conference Proceeding
Publication Date
11-1-2020
Abstract
Financial analysts' earnings forecast is one of the most critical inputs for security valuation and investment decisions. However, it is challenging to utilize such information for two main reasons: missing values and heterogeneity among analysts. In this paper, we show that one recent breakthrough in nonlinear tensor completion algorithm, CoSTCo [1], overcomes the difficulty by imputing missing values and significantly improves the forecast accuracy in earnings. Compared with conventional imputation approaches, CoSTCo effectively captures latent information and reduces the tensor completion errors by 50%, even with 98% missing values. Furthermore, we show that using firm characteristics as auxiliary information we can improve firms' earnings prediction accuracy by 6%. Results are consistent using different performance metrics and across various industry sectors. Notably, the performance improvement is more salient for the sectors with high heterogeneity. Our findings imply the successful application of advanced ML techniques in a real financial problem.
Identifier
85101317534 (Scopus)
ISBN
[9781728190129]
Publication Title
IEEE International Conference on Data Mining Workshops Icdmw
External Full Text Location
https://doi.org/10.1109/ICDMW51313.2020.00059
e-ISSN
23759259
ISSN
23759232
First Page
377
Last Page
384
Volume
2020-November
Recommended Citation
Uddin, Ajim; Tao, Xinyuan; Chou, Chia Ching; and Yu, Dantong, "Nonlinear Tensor Completion Using Domain Knowledge: An Application in Analysts' Earnings Forecast" (2020). Faculty Publications. 4862.
https://digitalcommons.njit.edu/fac_pubs/4862
