Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Characterizing Business Resilience Using SVM-Based Predictive Modeling
Trilobyte Statistical Software, Ltd..
University of Borås, Faculty of Textiles, Engineering and Business. (Textile Management)ORCID iD: 0000-0003-2015-6275
East Carolina State University.
Technical University of Liberec.
2016 (English)In: Meeting on Statistics in Business and Industry / [ed] Universitat Politècnica de Catalunya, Department of Statistics and Operations Research, Barcelona, Spain, 2016, 39-40 p.Conference paper, Oral presentation with published abstract (Other academic)
Sustainable development
The content falls within the scope of Sustainable Development
Abstract [en]

Business resilience has gained prominence, in academia and practice, vis-à-vis the heightened challenges recently faced by organizations, e.g. financial crisis. Developing resilience by thriving or bouncing back from crises yields sound business health in the future.However extant scholarly discussion on predictive modelling of economic resilience is rather limited, while business health studies are mainly limited to bankruptcy failure predictions. These studies mostly utilize financial snapshots (based on only few years data) to construct the predictive models hence are static in nature (Balcaen and Ooghe 2006). Several assumptions underpin these static models, e.g. considering failure as a steady process devoid of organizational history (Appiah et al. 2015, du Jardin and Séverin 2011). Even though, few recent studies (cf. du Jardin and Séverin (2011), Chen et al. (2013) etc.) have designed a “trajectory of corporate collapse” to forecast the changes in firms’ financial health, using various ‘expert systems’ like self-organizing maps (SOM) based upon unsupervised neural network approach, these studies still interpret the findings largely for predicting bankruptcy (a ‘state’) rather than drawing inference on the economic growth or recovery patterns (a ‘trajectory’) of organizations – a key to generate resilience. Neither these studies utilize longitudinal financial data (spanning over many years) to capture the dynamics of corporate history required to build resilience of organizations in reality.In this context, our paper proposes developing a predictive econometric model of business resilience by using ‘expert’ SVM method. The expanded predictor based on financial ratios highlighted by Altman (1968)’s Z-score also takes into consideration the corporate dynamics (first and second derivatives). Historical financial data is gathered from 198 firms representing 26 Dow Jones industrial sectors, and starting from 1960s.Our prediction model achieved comparatively high predictive accuracy of ---- (for a forecasting horizon of ----- years) and is comparable to similar studies. However, the main contribution of the paper is in proposing four archetypical patterns in business health trajectories, derived from the historical hind-sight, defined by tendency-dynamics combinations and is essential to characterize business resilience as follows:

Business Health (at T = t+1) = Business Health (T = 0 to t) + Resilience function

These four typical situations range from the most pessimistic case (tendency = Down, dynamics = Down) to the most promising (Up-Up). The four archetypes can be used to explain four resilience functions, viz. (i): up-up as sustainable resilience, (ii) up-down as short-term resilience, till t = T, (iii) down-up as resilience in near-future, at t = T, and (iv) down-down as lack of resilience.

Place, publisher, year, edition, pages
Barcelona, Spain, 2016. 39-40 p.
National Category
Probability Theory and Statistics Economics and Business
Research subject
Bussiness and IT
Identifiers
URN: urn:nbn:se:hb:diva-10599OAI: oai:DiVA.org:hb-10599DiVA: diva2:955453
Conference
International Symposium on Business and Industrial Statistics, Barcelona, June 8-10, 2016
Available from: 2016-08-25 Created: 2016-08-25 Last updated: 2017-05-02Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Pal, Rudrajeet
By organisation
Faculty of Textiles, Engineering and Business
Probability Theory and StatisticsEconomics and Business

Search outside of DiVA

GoogleGoogle Scholar

Total: 38 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf