TY - GEN
T1 - Nonlinear Tensor Completion Using Domain Knowledge
T2 - 20th IEEE International Conference on Data Mining Workshops, ICDMW 2020
AU - Uddin, Ajim
AU - Tao, Xinyuan
AU - Chou, Chia Ching
AU - Yu, Dantong
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11
Y1 - 2020/11
N2 - 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.
AB - 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.
KW - Convolutional Neural Network
KW - Finance
KW - Firm Earnings Forecast
KW - Nonlinear Tensor Factorization
KW - Sparse Tensor Completion
UR - http://www.scopus.com/inward/record.url?scp=85101317534&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101317534&partnerID=8YFLogxK
U2 - 10.1109/ICDMW51313.2020.00059
DO - 10.1109/ICDMW51313.2020.00059
M3 - Conference contribution
AN - SCOPUS:85101317534
T3 - IEEE International Conference on Data Mining Workshops, ICDMW
SP - 377
EP - 384
BT - Proceedings - 20th IEEE International Conference on Data Mining Workshops, ICDMW 2020
A2 - Di Fatta, Giuseppe
A2 - Sheng, Victor
A2 - Cuzzocrea, Alfredo
A2 - Zaniolo, Carlo
A2 - Wu, Xindong
PB - IEEE Computer Society
Y2 - 17 November 2020 through 20 November 2020
ER -