• ALTAMAS KHAN
• DR. BONTHU KOTAIAH

Various clustering algorithms have been developed to crew data into clusters in diverse domains. Nevertheless, these clustering algorithms work with no trouble either on pure numeric data or on pure specific information, most of them perform poorly on combined categorical and numeric information forms. In this paper, a brand new two-step clustering approach is offered to find clusters on this type of data. On this procedure the objects in specific attributes are processed to construct the similarity or relationships among them founded on the ideas of co-incidence; then all express attributes may also be converted into numeric attributes founded on these built relationships. Subsequently, when you consider that all categorical information are modified into numeric, the present clustering algorithms can be applied to the dataset without anguish. Nonetheless, the prevailing clustering algorithms endure from some risks or weak point, the proposed two-step method integrates hierarchical and partitioning clustering algorithm with including attributes to cluster objects. This system defines the relationships amongst gadgets, and improves the weaknesses of applying single clustering algorithm. Experimental evidences exhibit that strong results will also be accomplished by way of applying this process to cluster blended numeric and categorical knowledge.

clustering algorithms, educational data Set, K-means

"STUDENT RESULT ANALYSIS USING CLUSTERING TECHNIQUE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.1-5, April-2019, Available :http://www.jetir.org/papers/JETIR1904401.pdf

"STUDENT RESULT ANALYSIS USING CLUSTERING TECHNIQUE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp1-5, April-2019, Available at : http://www.jetir.org/papers/JETIR1904401.pdf