Abstract: Classification is supervised learning technique in data mining that produces a learned model from a labelled dataset. Many classification algorithms are available to solve binary classification problem where there are only two possible values of class label. Multiclass classification deals with the classification problem where class label has more than two possible values. Multiclass classification problems are highly relevant in recent machine learning developments, because there are numerous real life applications that rely on high number of parameters and classes. For example genetics, banking, physics, medical and other applications.  In this paper we discussed techniques of multiclass classification and challenges in field of data mining.

Keywords: Classification, Data Mining, Multiclass Data, One-vs-One, One-vs-All, ECOC

Cite:
Komal Shah, Dr. Kajal S. Patel*,"Study of Multiclass Classification Techniques", IARJSET International Advanced Research Journal in Science, Engineering and Technology, vol. 11, no. 2, 2024, Crossref https://doi.org/10.17148/IARJSET.2024.11220.

| DOI: 10.17148/IARJSET.2024.11220