Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Chapter 7 - Predicting financial risk from revenue reports

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Author(s): Qian, B.; Li, H.
  • Source:
    In Big Data and Smart Service Systems 2017:99-113
  • Publication Information:
    Elsevier Inc.
  • Document Type:
    Book Chapter
  • Additional Information
    • Affiliation:
      IBM Thomas J. Watson Research Center, Yorktown Heights, NY, United States
    • Keywords:
      Financial risk prediction
      learning to rank
      kernel methods
      data mining
      machine learning
    • Abstract:
      This chapter investigates methods of predicting the financial risk of publicly traded corporations using their revenue reports. Unlike many existing algorithms, where a prediction model is learnt using real-valued ground truth risks, we propose to solve the prediction as a learning-to-rank problem with pairwise constraints (e.g., company A is financially more stable than company B). To further increase the flexibility of our approach, we solve the pairwise learning formulation in its dual format, which makes our model nonlinear and thereby it can be applied to complex prediction tasks. The advantage of using pairwise supervision is not only limited to the simplified acquisition of training data, but it also produces new problem settings. We explore one such setting in which the prediction model can actively ask humans informative questions so as to improve prediction accuracy. Our work aims to address three limitations of existing works: (1) pointwise supervision—we adopt pairwise supervision which reduces the cost of collecting training samples; (2) linearity—we kernelize the formulation to make it nonlinear, which broadens its applicability; and (3) training data bottleneck—the proposed model can actively integrate humans into the learning loop, so that when the initial training samples do not carry enough knowledge, additional examples can be added to create a better prediction model. Using the proposed efficient optimization method, we evaluate our approach using real-text files (annual revenue reports) and compare with state-of-the-art methods. The results unequivocally demonstrate the superior performance of our proposed approach, and validate the effectiveness of our active knowledge injection in the context of human–machine interaction.
    • ISBN:
      978-0-12-812013-2
    • ISBN:
      978-0-12-812040-8
    • ISBN:
      0-12-812013-4
    • ISBN:
      0-12-812040-1
    • Accession Number:
      10.1016/B978-0-12-812013-2.00007-1
    • Accession Number:
      B9780128120132000071
    • Copyright:
      Copyright © 2017 Zhejiang University Press Co., Ltd. Published by Elsevier Inc. All rights reserved.
  • Citations
    • ABNT:
      QIAN, B.; LI, H. Chapter 7 - Predicting financial risk from revenue reports. Big Data and Smart Service Systems, [s. l.], p. 99–113, 2017. DOI 10.1016/B978-0-12-812013-2.00007-1. Disponível em: http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edselp&AN=B9780128120132000071. Acesso em: 29 set. 2020.
    • AMA:
      Qian B, Li H. Chapter 7 - Predicting financial risk from revenue reports. Big Data and Smart Service Systems. January 2017:99-113. doi:10.1016/B978-0-12-812013-2.00007-1
    • APA:
      Qian, B., & Li, H. (2017). Chapter 7 - Predicting financial risk from revenue reports. Big Data and Smart Service Systems, 99–113. https://doi.org/10.1016/B978-0-12-812013-2.00007-1
    • Chicago/Turabian: Author-Date:
      Qian, B., and H. Li. 2017. “Chapter 7 - Predicting Financial Risk from Revenue Reports.” Big Data and Smart Service Systems, January, 99–113. doi:10.1016/B978-0-12-812013-2.00007-1.
    • Harvard:
      Qian, B. and Li, H. (2017) ‘Chapter 7 - Predicting financial risk from revenue reports’, Big Data and Smart Service Systems, pp. 99–113. doi: 10.1016/B978-0-12-812013-2.00007-1.
    • Harvard: Australian:
      Qian, B & Li, H 2017, ‘Chapter 7 - Predicting financial risk from revenue reports’, Big Data and Smart Service Systems, pp. 99–113, viewed 29 September 2020, .
    • MLA:
      Qian, B., and H. Li. “Chapter 7 - Predicting Financial Risk from Revenue Reports.” Big Data and Smart Service Systems, Jan. 2017, pp. 99–113. EBSCOhost, doi:10.1016/B978-0-12-812013-2.00007-1.
    • Chicago/Turabian: Humanities:
      Qian, B., and H. Li. “Chapter 7 - Predicting Financial Risk from Revenue Reports.” Big Data and Smart Service Systems, January 1, 2017, 99–113. doi:10.1016/B978-0-12-812013-2.00007-1.
    • Vancouver/ICMJE:
      Qian B, Li H. Chapter 7 - Predicting financial risk from revenue reports. Big Data and Smart Service Systems [Internet]. 2017 Jan 1 [cited 2020 Sep 29];99–113. Available from: http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edselp&AN=B9780128120132000071