Machine Learning Techniques for Predictive Modelling: A Review

Running head: COMPUTER SCIENCE
COMPUTER SCIENCE
Name of the Student
Name of the University
Author Note

1COMPUTER SCIENCE
Literature Review
In this particular chapter, all the required background information concerning the main
idea of the thesis has been given1. The thesis also discusses the SVM learning technique which is
needed for producing a classification model. This particular model also highlights aboutSVM
classifier — the information focuses on the idea of machine learning techniques which has
helped the officer in solving this case. It will ultimately help in solving various kinds of issues or
cases. The background information helps in having an idea regarding graphical interface that
provides an easy way for securing both data and enabling the use of police based services2. There
are various kinds of predictive modelling techniques which are available in the present scenario.
It is considered to be free from commercially-based software. The subsequent section of the
report mainly deals with implementation of predictive modelling technique which has been
discussed in details.
Machine learning depends on the ability of various systems to learn and implement new
techniques of human interface efficiently. Machine algorithm is mainly used for the purpose of
prediction and description. Machine learning algorithm is used for explaining in a better way
with the help of linear classifier in the machine world. A proper idea has been provided
concerning the application of machine learning classification. It is mainly used for understanding
1Mercier, G., and M. Lennon (2003), Support vector machines for hyperspectral image classification with spectral-
based kernels, in Geoscience and Remote Sensing Symposium, 2003. IGARSS’03. Proceedings. 2003 IEEE
International, vol. 1, pp. 288–290, IEEE.
2. Marr, B. (2016), A short history of machine learning-every manager should read, Forbes.URL: https://www.
Forbes. com/sites/bernardmarr/2016/02/19/a-short history-of-machine-learning-every-managershould-read.

2COMPUTER SCIENCE
the various kinds of risks related to diseases which are encountered in MRI structure. Its
application helps in analysing machine learning based algorithm by making use of the MRI
approach. The MRI structure of brain highlights that there is no direct way which is needed for
finding data from clinical practice3. It has been implemented so that machine learning based
application can be easily used for the diagnosis of MRI data. In this particular application, both
kind of SVM and Naïve Bayes can be easily used for classification of MRI data. In this specific
application, both the methods of SVM and Naïve Bayes can be easily used for responding and
prediction of treatment. In some of the general cases, MRI brain application makes use of SVM,
which provides a value between the given value of 67.6 and 90.3. MRI brain application is used
for calculating the overall accuracy for predicting treatment response. This particular study
highlights specific sets of genes which are considered to be similar to the method of expression
data4. It mainly highlights various kinds of SVM model along with a different variety of metrics.
SVM model has been implemented so it can easily classify the given genes by making use of the
proper expression. The dataset which is used in this expression comes up with genes of records
that have 79 different DNA microarrays.Kernel-based functions in the SVM model which comes
up with the best prediction for unannotated along with identifying the role of yeast genes. The
ultimate focus is on the fact that SVM methods and predictive analytics can be used for
3Kim, Y.-K., and K.-S. Na (2018), Application of machine learning classification for structural brain mri in mood
disorders: a Critical review from a clinical perspective, Progress in Neuro Psychopharmacology and Biological
Psychiatry, 80, 71–80
4: Furey, T. S., N. Cristianini, N. Duffy, D. W. Bednarski, M. Schummer, and D. Haussler (2000), Support vector
machine classification and validation of cancer tissue samples using microarray expression data, Bioinformatics, 16
(10), 906–914.