Data Mining §

• Data Mining: is training an algorithm with a dataset that we know both the Independent Variable and Dependent Variable of. Then Using it on a new dataset to predict the unknown IV

Data Mining Methods §

• Decision Trees Analysis: used to classify and sub-classify data to predict what possibilities of their IV could be

Regression Analysis §

• Checks if, and by how much Independent Variable (s) affect Dependent Variable
  • $R^2$ (0-1) the % that the IV(s) account for the changes in the DV >0.5
  • Significance (Sig.) must be <0.05 to be statistically significant
  • Coefficient: the percentage of each the independent variables is responsible for changes in the dependent variable
  • Standard Error: amount by which the coefficient varies across different cases
  • t-value of the test and its value: is equal to the coefficient divided by the standard error.

• Artificial Neural Networks: AI & ML learns from large amounts of past data to predict future data
• Cluster Analysis: dividing a database into clusters grouped by similarities/dissimilarities to divide and conquer large databases
• Associate Rule Mining: some data values can commonly be found together such as Toothpaste and Toothbrushes, which can be put into the same bucket and more likely to be sale bundled together
• Text Mining

Data Visualization Project §

• Data Visualization Project Bangkok Weather