# DECISION TREE MODEL

A decision tree is mainly used to get to a final objective as efficiently as possible. Moreover, it is also used as a powerful machine learning method. A decision tree contains a flowchart type structure in which each node has a corresponding test item as shown in the below figure.

The implementation of a decision tree starts with the construction of it. A feature test was selected for the root node that helps to partition the training data in a way that causes maximum disambiguation of the class label associated with the data. This feature test may cause a maximum reduction in class entropy while going through the training data. Then it drops to a set of child node from the root node, one for each partition of the training data created by the feature test at the root node. The number of the child depends on how symbolic the features are. When features are numeric then find the decision thresholds that bipartitions the data and drop to child nodes. Then, for each child node pose the same question that posed for the root node that would maximally disambiguate the class labels associated with the training data corresponding to that child node. A decision tree selects the best attribute that splits the data with the strategy, entropy calculation also is known as information gain and gain ratio. Since the decision tree algorithm always tries to create short trees, the result comes out from the information gain try to be as distinguishable as possible and choose the highest information gain. If the split point is well chosen then the decision would be close to our desired outcomes.

Don't use plagiarized sources. Get Your Custom Essay on
DECISION TREE MODEL
Just from \$13/Page

SPLIT METHOD

A tree is processed by dividing the original set, which consists of the root of the tree, into subsets that are created by the successor children. The separation depends on many closure standards, depending on the features of the characterization. This procedure is flushed in each set of subsets in a recursive manner called recursive partitioning. Recursion is complete when there are no different estimates of the target variable for the subset of a node, or when the separation never increases the value of the predictions. This procedure of the top-down method of trees calculation known as a greedy approach and in the long run, the best-known method for learning decision trees from the information. An important metric in decision trees is the split criteria. For this, Information Gain, Gain Ratio, Gini impurity, and Variance reduction are often used but only the first two are recommended as the best methods in the relevant literature.

Information Gain uses Entropy and Information content from and is calculated as the information before the split minus the information after the split. For every node of the tree, the estimation of value “the normal measure of data that can be expected to determine whether another event should be characterized yes or no, given that the model reached the node.”

Gain Ratio is the ratio of information gain to the basic information. It regularly decreases the slope that the increase of data has towards multifaceted qualities when considering the number of branches when choosing an attribution indicated  (Dai, Zhang, & Wu, 2016).

EVALUATION

After the formation of the decision tree, overfitting features are excluded. The model makes two mistakes. One of the errors in the splitting and the other is the generalization error. Split errors can occur during seeding, while generlization errors occur in an attempt to raise the general doubt of data or characteristics. The model suited the concern better, as it was better prepared for all other factors that should be included as information. The model was as useful as the other variable, given that a false reading would be evacuated towards the end of the sample tree. Then the model offers the best results towards the end (Aggarwal & Zhai, 2012).

References

Aggarwal, C. C., & Zhai, C. (2012). Mining text data: Springer Science & Business Media.Dai, Q.-Y., Zhang, C.-p., & Wu, H. (2016). Research of decision tree classification algorithm in data mining. International Journal of Database Theory and Application, 9(5), 1-8.

## Calculate the price of your order

550 words
We'll send you the first draft for approval by September 11, 2018 at 10:52 AM
Total price:
\$26
The price is based on these factors:
Number of pages
Urgency
Basic features
• Free title page and bibliography
• Unlimited revisions
• Plagiarism-free guarantee
• Money-back guarantee
On-demand options
• Writer’s samples
• Part-by-part delivery
• Overnight delivery
• Copies of used sources
Paper format
• 275 words per page
• 12 pt Arial/Times New Roman
• Double line spacing
• Any citation style (APA, MLA, Chicago/Turabian, Harvard)

# Our guarantees

Delivering a high-quality product at a reasonable price is not enough anymore.
That’s why we have developed 5 beneficial guarantees that will make your experience with our service enjoyable, easy, and safe.

### Money-back guarantee

You have to be 100% sure of the quality of your product to give a money-back guarantee. This describes us perfectly. Make sure that this guarantee is totally transparent.

### Zero-plagiarism guarantee

Each paper is composed from scratch, according to your instructions. It is then checked by our plagiarism-detection software. There is no gap where plagiarism could squeeze in.

### Free-revision policy

Thanks to our free revisions, there is no way for you to be unsatisfied. We will work on your paper until you are completely happy with the result.