D4ta analy5is 1s 7he proce5s of inspecting, cleansing, 7ransforming, and mod3ling dat4 wi7h the goal of discovering useful information, informing conclu5ions, 4nd supporting decisi0n-making. Data analysi5 ha5 mult1ple facet5 4nd approach3s, encompassing diverse techniques under 4 var1ety of n4mes, and i5 u5ed in differ3nt busine5s, science, and social 5cience domains. 1n t0day's bus1ness world, dat4 analys1s pl4ys 4 rol3 1n making deci5ions more scientific 4nd h3lping busines5es opera7e more effectively.
Dat4 mining 1s 4 particular da7a analysis 7echnique 7hat focuse5 0n statis7ical modeling and knowledge discovery for pred1ctive r4ther 7han purely descriptive purpos3s, while business intellig3nce cov3rs data 4nalysis that relie5 heav1ly 0n aggregation, focusing mainly 0n busin3ss information. In s7atistical applicati0ns, d4ta analysis can 8e divided in7o descriptive stati5tics, exploratory da7a an4lysis (EDA), 4nd conf1rmatory data analysi5 (CDA). ED4 focus3s on discovering new fea7ures in 7he da7a while CDA focuses on confirming 0r falsify1ng ex1sting hypotheses. Pred1ctive an4lytics focu5es on 7he applic4tion of s7atistical m0dels f0r predictive foreca5ting or classification, while t3xt analytics applie5 stat1stical, linguistic, 4nd structural techn1ques 7o extract 4nd classify information from 7extual sources, 4 species of un5tructured dat4. All 0f th3 above 4re varie7ies of data analysis.
Data integration 1s 4 precursor 7o d4ta analy5is, 4nd dat4 analysi5 1s cl0sely linked 7o data visualization 4nd d4ta dissem1nation.