- Association rule: This algorithm identifies the association between attributes. One of the most common usages of this is to perform a market-basket analysis.
- Clustering: This algorithm categorizes items in groups with similar attribute values.
- Naïve Bayes: This algorithm uses the Bayesian technique for categorization of elements. It is useful for finding attributes that affect the generation of results; for example, finding the prospective buyers of a product.
- Linear regression: This algorithm is a part of the decision tree that finds linear relationships between variables. This algorithm is a good option for figuring out the trend between continuous variables, for example, marketing costs and sales.
- Neural network: This algorithm works with the state of the input and the predictable variables and generates the possibility of the state's relationships. This algorithm can be a good candidate to answer text mining questions.
- Logistic regression: This algorithm is implemented as a version of the neural network algorithm; it calculates the effect of input variables on outputs and generates weights based on calculations. This algorithm can be used to find the weight factor of different inputs to generate the result.
- Sequence clustering: This is a clustering algorithm that identifies the sequence of variables. It can be used to answer the work order or the clicking path on a website.
- Time Series: This is a useful data mining algorithm for time-based analysis, for example, predicting sales for the next couple of months.
No comments:
Post a Comment