Discussion Forum Unit 5

Conduct research on the internet and in the University of the People library on the topic of
decision trees for classification. Based upon your research, identify at least two use cases
(problems or opportunities where you would use a decision tree to solve the problem) for
decision trees and describe how decision tree learning could be used as a solution for the use
case.
One example (which you may NOT use) is training a decision tree to make a decision whether
to approve a home mortgage based upon a number of data elements including the
creditworthiness of the mortgage applicant and the value and characteristics of the property
being mortgaged.
Use the Internet and the University of the People library to conduct your research. Make sure
that you are citing your sources. Since this assignment will require significant research you
must include at least two sources in your response.

Within Machine learning classification techniques, the method that uses a decision tree for
classification is another alternative in building prediction models apart of the techniques
studied so far in this class. This method is a learning model used to predict target based on the
decision rules learned from the features in the training dataset that divide the dataset” based
on asking a series of questions” (Li, 2019, para 1 ).
Even if in many cases the decision tree is not so precise as other methods ( Linear regression,
KNN, or Logistic regression) they are instead easy to understand or explain as they “closely
mirror human
a decision-making “(James, Witten, Hastie, & Tibshirani, 2013, p. 315) and can better handle
the qualitative descriptors features without the need of using dummy variables(James, Witten,
Hastie, & Tibshirani, 2013). However the accuracy of the prediction using the decision trees
method can be improved by aggregating many decision trees using methods like boosting,
Random Forests or Bagging(James, Witten, Hastie, & Tibshirani, 2013).
One use case where the decision tree method of classification better fit than other
classification techniques is to predict the online consumer market user behavior by using the
ID3 algorithm and the information gain to “measure how different attributes help the tree split
the set into smaller subsets” (Fokin & Hagrot, 2015, p3). Using this approach the decision tree
model can be applied to each product within the dataset and analyze the information gain
levels by maximizing the predictive model-based on better distribution of the features maximum
gain distribution correlated with the splits within the root of the decision tree(Fokin & Hagrot,
2015).
Another case when using the decision trees to create a prediction models is a more complex
approach in machine learning and is described in the article “Multi-modal Score Fusion and
Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs” (Kaya,
G¨urpınar, & Salah, 2017), a study showing the application of Machine learning and specifically
the decision trees in automating the screening of potential job candidates' video CV’s. Within
the model are used features computed from the video file by analyzing audio, face and scene
that are “ fed into modality-specific regressors to predict apparent personality traits and a
variable that predicts whether the subject will be invited to the interview” (Kaya, G¨urpınar, &
Salah, 2017, para 1).
Following is the flowchart of the proposed solution where the use of the Random forests
decision tree method leads to the prediction model proposed.

This study source was downloaded by 100000813700581 from CourseHero.com on 12-15-2021 19:29:37 GMT -06:00

https://www.coursehero.com/file/77098846/Discussion-Forum-Unit-5docx/
 (Kaya, G¨urpınar, & Salah, 2017)

References
Fokin, D., & Hagrot, J. (2015, May 11). Constructing decision trees for user behavior prediction
in the online consumer market. Retrieved from http://www.diva-
portal.org/smash/get/diva2:927446/FULLTEXT01.pdf
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning
with applications in R. New York, NY: Springer. Retrieved from http://www-
bcf.usc.edu/~gareth/ISL/ISLR%20First%20Printing.pdf
Kaya, H., G¨urpınar, F., & Salah, A. (2017, July). Multi-modal Score Fusion and Decision Trees
for Explainable Automatic Job Candidate Screening from Video CVs. Retrieved from
https://www.researchgate.net/publication/317231935_Multi-
modal_Score_Fusion_and_Decision_Trees_for_Explainable_Automatic_Job_Candidate_Scree
ning_from_Video_CVs
Li, L. (2019, May 16). Classification and Regression Analysis with Decision Trees. Retrieved
from https://towardsdatascience.com/https-medium-com-lorrli-classification-and-regression-
analysis-with-decision-trees-c43cdbc58054

This study source was downloaded by 100000813700581 from CourseHero.com on 12-15-2021 19:29:37 GMT -06:00

https://www.coursehero.com/file/77098846/Discussion-Forum-Unit-5docx/
Powered by TCPDF (www.tcpdf.org)