The use of modern data mining techniques on large datasets has become a recent phenomenon across a broad range of applications. One of the most frequent tasks is to build statistical models using historical data and utilize them to predict new, so far unclassified, cases. This article examines the problem of predicting a military interstate dispute between two states (dyad) by employing selected data mining techniques. Suitable methods are identified and applied to the existing dataset of politically relevant dyads. The result is the building of statistical models for the classification of potential dyadic conflicts. The overall performance of these models is verified and cost analysis is done based on the different impacts of incorrect classification. The results are compared with those of other published research studies in the field of conflict prediction; the models created by data mining techniques significantly outperform all rival algorithms and approaches. Finally, the last part of the article presents the results of applying data mining techniques to association, i.e. to discovering relationships and dependencies in the data.
PalmerGD’OrazioVKenwickM, et al. The MID4 Dataset, 2002–2010: Procedures, coding rules and description. Conflict Manage Peace Sci2015; 32(2): 222–242.
5.
COW: The Correlates of War Project: About the Correlates of War Project. Available at: http://www.correlatesofwar.org/ (2000–2020, accessed 13 May, 2019).
6.
UCPD: Uppsala Conflict Data Program. Available at: https://ucdp.uu.se/ (2018, accessed 13 May, 2019).
7.
HIIC: Heidelberg Institute for International Conflict Research. Available at: https://hiik.de/ (2019, accessed 5 December, 2019).
8.
Heidelberg Institute for International Conflict Research. Conflict Barometer 2018. Heidelberg: Heidelberg Institute for International Conflict Research, 2018.
9.
RayJL. Explaining interstate conflict and war: What should be controlled for?Conflict Manage Peace Sci2003; 20(1): 1–32.
AchenC. Toward a new political methodology: Microfoundations and ART. Annu Rev Polit Sci2002; 5(1): 423–450.
12.
OnealJRRussettB. Rule of three, let it be? When more really is better. Conflict Manage Peace Sci2005; 22(4): 293–310.
13.
CollierPHoefflerA. On the incidence of civil war in Africa. J Conflict Resolut2002; 46(1): 13–28.
14.
FearonJDLaitinDD. Ethnicity, insurgency, and civil war. Am Polit Sci Rev2003; 97(1): 75–90.
15.
WarrenCT. Modeling the coevolution of international and domestic institutions: Alliances, democracy, and the complex path to peace. J Peace Res2016; 53(3): 424–441.
16.
GrantKA. Outsourcing security: Alliance portfolio size, capability, and reliability. Int Stud Q2013, 57(2): 418–429.
17.
KimHMRousseauDL. The reciprocal relationship between military conflict and democracy. Defence Peace Econ2013; 24(1): 47–72.
18.
MangerMSPickupMA. The coevolution of trade agreement networks and democracy. J Conflict Resolut2014; 60(1): 164–191.
19.
MaozZ. Networks of Nations: The Evolution, Structure, and Impact of International Networks, 1816–2001. New York: Cambridge University Press, 2010.
SullivanPL. Who Wins? Predicting Strategic Success and Failure in Armed Conflict. New York: Oxford University Press, 2012.
22.
MarwalaT. Modeling interstate conflict: The role of economic interdependency for maintaining peace. In: Advanced Information and Knowledge Processing, London: Springer-Verlag, 2013, pp. 233–252.
23.
MarwalaT. Rational counterfactuals and decision making: Application to interstate conflict. In: Marwala TAdvanced Information and Knowledge Processing. London: Springer-Verlag, 2014, pp. 73–89.
24.
ReiterDStamACHorowitzMC. A revised look at interstate wars, 1816–2007. J Conflict Resolut2014; 60 (5): 956–976.
25.
GiblerDMMillerSVLittleEK. An analysis of the militarized interstate disputes dataset, 1816–2001. Int Stud Q2016; 60(4): 719–730.
26.
MaozZJohnsonPLKaplanJ, et al. The dyadic militarized interstate disputes (MIDs) dataset version 3.0: Logic, characteristics, and comparisons to alternative datasets. J Conflict Resolut2019; 63(3): 811–835.
27.
KingMLHeringASNewmanAM. Evaluating counterinsurgency classification schemes. Mil Oper Res2014; 19(3): 5–25.
28.
KisielewskiMRosaJCAsherJ. Statistical Approaches to Developing Indicators of Armed Violence. Geneva: Technical paper by StratAid for Small Arms Survey, 2010.
29.
GoldstoneJABatesRHEpsteinDL, et al. A global forecasting model of political instability. Am J Polit Sci2010; 54(1): 190–208.
30.
BoekesteinBC. A Predictive Model of World Conflict using Open Source Data. Wright-Patterson Air Force Base, Ohio: Air Force Institute of Technology, 2015.
31.
AhnerDKShallcrossNJ. A Conditional Logistic Regression Predictive Model of World Conflict using Open Source Data. Wright-Patterson Air Force Base, Ohio: Air Force Institute of Technology, 2016.
32.
Institute for Economics & Peace. Risk Report 2017: New Methods to Assess Risk of Conflict and Violence. Report number 52. Available at: http://visionofhumanity.org/reports (2017, accessed 16 May 2019).
33.
MarwalaTLagazioMTetteyT. An integrated human–computer system for controlling interstate disputes. Int J Comput Appl2009; 31(4): 239–246.
34.
CranmerSJDesmaraisBA. A critique of dyadic design. Int Stud Q2016; 60(2): 355–362.
35.
RussettBOnealJR. Triangulating Peace: Democracy, Interdependence, and International Organizations. New York: WW Norton & Company, 2000.
36.
HolteRC. Very simple classification rules perform well on most commonly used datasets. Machine Learning1993; 11: 63–91.
SilvaLMarquesdeSáJAlexandreLA. Data classification with multilayer perceptrons using a generalized error function. Neural Netw2008; 21(9): 1302–1310.
39.
DreiseitlSOhno-MachadoL. Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform2002; 35(5–6), 352–359.
40.
FrankEWittenIH. Generating accurate rule sets without global optimization. In: ICML ’98: Proceedings of the Fifteenth International Conference on Machine Learning, 1998, pp. 144–151. San Francisco: Morgan Kaufmann Publishers.
41.
SamworthRJ. Optimal weighted nearest neighbour classifiers. Ann Statist2012; 40(5): 2733–2763.
42.
QuinlanJR. C4.5: Programs for Machine Learning. San Mateo: Morgan Kaufmann Publishers, 1993.
43.
BreimanL. Random forests. Machine Learning2001; 45(1): 5–32.
44.
AgrawalRSrikantR. Fast algorithms for mining association rules in large databases. In: VLDB '94: Proceedings of the 20th International Conference on Very Large Data Bases, 1994, pp. 478–499. San Francisco: Morgan Kaufmann Publishers.
45.
LiuBHsuWMaY. Integrating Classification and Association Rule Mining. In: KDD '98: Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining, 1998, pp. 80–86. Palo Alto: AAAI Press.
46.
WittenIHFrankEHallMA. Data Mining: Practical Machine Learning Tools and Techniques. Burlington: Morgan Kaufmann, 2016.
