scholarly journals AN EFFECTIVE MACHINE LEARNING MODEL FOR CUSTOMER ATTRITION PREDICTIONIN MOTOR INSURANCE USING GWO-KELM ALGORITHM

2021 ◽  
Vol 9 (1) ◽  
pp. 91-105
Author(s):  
Deepthi Das, Raju Ramakrishna Gondkar
Keyword(s):  
Machine Learning ◽  
Missing Values ◽  
Insurance Industry ◽  
Expectation Maximization Algorithm ◽  
Insurance Sector ◽  
Industrial Sectors ◽  
Machine Learning Model ◽  
Motor Insurance ◽  
Bayes Algorithm ◽  
Customer Attrition

The prediction of customers' churn is a challenging task in different industrial sectors, in which the motor insurance industry is one of the well-known industries. Due to the incessant upgradation done in the insurance policies, the retention process of customers plays a significant role for the concern. The main objective of this study is to predict the behaviors of the customers and to classify the churners and non-churners at an earlier stage.  The Motor Insurance sector dataset consists of 20,000 records with 37 attributes collected from the machine learning industry. The missing values of the records are analyzed and explored via Expectation Maximization algorithm that categorizes the collected data based on the policy renewals. Then, the behavior of the customers are also investigated, so as to ease the construction process training classifiers. With the help of Naive bayes algorithm, the behaviors of the customers on the upgraded policies are examined. Depending on the dependency rate of each variable, a hybrid GWO-KELM algorithm is introduced to classify the churners and non-churners by exploring the optimal feature analysis. Experimental results have proved the efficiency of the hybrid algorithm in terms of 95% prediction accuracy; 97% precision; 91% recall & 94% F-score.

The Sentiment Analysis Reviewing Indosat Services from Twitter Using the Naive Bayes Classifier

2020 ◽  
Vol 1 (2) ◽  
pp. 61-66
Author(s):  
Febri Astiko ◽  
Achmad Khodar
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Naive Bayes ◽  
Learning Model ◽  
Naïve Bayes ◽  
Bayes Classifier ◽  
Naïve Bayes Classifier ◽  
Machine Learning Model ◽  
Bayes Algorithm

This study aims to design a machine learning model of sentiment analysis on Indosat Ooredoo service reviews on social media twitter using the Naive Bayes algorithm as a classifier of positive and negative labels. This sentiment analysis uses machine learning to get patterns an model that can be used again to predict new data.

scholarly journals Big Five Personality Prediction from Social Media Data using Machine Learning Techniques

2020 ◽  
Vol 9 (4) ◽  
pp. 2412-2417
Keyword(s):  
Machine Learning ◽  
Big Five ◽  
Machine Learning Techniques ◽  
Big Five Personality ◽  
Learning Techniques ◽  
Machine Learning Model ◽  
Personality Prediction ◽  
Twitter Users ◽  
Bayes Algorithm ◽  
Media Data

Personality has been important for a number of types of cooperation; it has useful in predicting job achievement, expert and emotional relationship achievement, and even tendency towards a variety of interfaces. To accurately examine the characters of users, a personality test must be carried out. In numerous areas of online life it is usually impractical to use character research. . We used SVM classification, Random Forest algorithm, Naïve Bayes Algorithm and Logistic regression to comparatively predict the user’s personality accurately. The main goal of the paper is to evaluate the machine learning models using the four parameters- accuracy, precision, recall, f1 score and basing upon these parameters the best machine learning model will be used to classify the big five personality traits of the twitter users.

scholarly journals Auditor Choice Prediction Model Using Corporate Governance and Ownership Attributes: Machine Learning Approach

2021 ◽  
Vol 11 (7) ◽  
pp. 87-94
Author(s):  
Rahayu Abdul Rahman ◽  
◽  
Suraya Masrom ◽  
Nor Balkish Zakaria ◽  
Sunarti Halid
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Financial Reporting ◽  
Learning Algorithm ◽  
Stock Exchange ◽  
Features Selection ◽  
Firm Characteristics ◽  
Auditor Choice ◽  
Machine Learning Model ◽  
Bayes Algorithm

-External auditor is one of the governance mechanisms in mitigating corporate managerial misconduct and thereby enhance the credibility of accounting information. Thus, the main objective of this study is to develop machine learning prediction model on auditor choice of the firm which signal the quality of auditing and financial reporting processes.This paper presents the fundamental knowledge on the design and implementation of machine learning model based on four selected algorithms tested on the real dataset of 2,262 firm-year observations of companies listed on Malaysian stock exchange from 2000 to 2007. The performance of each machine learning algorithm on the auditor choice dataset has been observed based on three groups of features selection namely firm characteristics, governance and ownership. The findings indicated that the machine learning models present better accuracy performance with ownership features selection mainly with the Naïve Bayes algorithm. Keywords-Auditor Choice, Machine Learning, Prediction

scholarly journals Optimal Value Estimation of Intentional-Value-Substitution for Learning Regression Models

2021 ◽  
Vol 25 (2) ◽  
pp. 153-161
Author(s):  
Takuya Fukushima ◽  
Tomoharu Nakashima ◽  
Taku Hasegawa ◽  
Vicenç Torra ◽  
◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Error ◽  
Regression Models ◽  
Missing Values ◽  
Target Function ◽  
Training Dataset ◽  
Machine Learning Model ◽  
Optimal Value ◽  
Value Estimation ◽  
Feature Values

This paper focuses on a method to train a regression model from incomplete input values. It is assumed in this paper that there are no missing values in a training dataset while missing values exist during a prediction phase using the trained model. Under this assumption, we propose Intentional-Value-Substitution (IVS) training to obtain a machine learning model that makes the prediction error as minimum as possible. In IVS training, a model is trained to approximate the target function using a modified training dataset in which some feature values are substituted with a certain value even though their values are not missing. It is shown through a series of computational experiments that the substitution values calculated from a mathematical analysis help the models correctly predict outputs for inputs with missing values.

scholarly journals Missing data handling for machine learning models

2021 ◽  
Vol 10 (2) ◽  
pp. 123
Author(s):  
Karim H. Erian ◽  
Pedro H. Regalado ◽  
James M. Conrad
Keyword(s):  
Machine Learning ◽  
Missing Data ◽  
Missing Values ◽  
Learning Model ◽  
The Novel ◽  
Machine Learning Model ◽  
Missing Data Problem ◽  
User Data ◽  
One Machine ◽  
Novel Algorithm

This paper discusses a novel algorithm for solving a missing data problem in the machine learning pre-processing stage. A model built to help lenders evaluate home loans based on numerous factors by learning from available user data, is adopted in this paper as an example. If one of the factors is missing for a person in the dataset, the currently used methods delete the whole entry therefore reducing the size of the dataset and affecting the machine learning model accuracy. The novel algorithm aims to avoid losing entries for missing factors by breaking the dataset into multiple subsets, building a different machine learning model for each subset, then combining the models into one machine learning model. In this manner, the model makes use of all available data and only neglects the missing values. Overall, the new algorithm improved the prediction accuracy by 5% from 93% accuracy to 98% in the home loan example.

scholarly journals Is compulsory third party motor insurance the panacea for the South African insurance industry?

2014 ◽  
Vol 11 (4) ◽  
pp. 657-669
Author(s):  
Elton Zingwevu ◽  
Athenia Bongani Sibindi
Keyword(s):  
South Africa ◽  
Central Government ◽  
Insurance Industry ◽  
Safety Net ◽  
Road Accident ◽  
Third Party ◽  
Insurance Companies ◽  
Insurance Sector ◽  
Bodily Injury ◽  
Motor Insurance

Compulsory motor insurance schemes have gained prominence over the years as a policy prescription by governments in their quest to provide a safety net for the protection of consumers and insurers alike. By making as minimum, motor third party insurance compulsory, central government ensures that the burden of providing indemnity is removed from the fiscus and entrusted upon the insurance sector. This also proves to be mutually beneficial to the insurance companies as the risk pool is widened. Sadly South Africa does not have a fully-fledged motor third party compensation scheme but has a variant of such a scheme in the form of the Road Accident Fund. The limitations of this fund are that it only caters for motor third party liability for bodily injury or death and its limits of compensation are relatively low. In this article we demonstrate the need for policy makers in South Africa to reintroduce compulsory motor third party insurance in order to alleviate the burden of funding motor liability from the fiscus as well as to widen the risk pool of insurers.

Building a predictive model for warfarin dosing via machine learning

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
O Tan ◽  
J.Z Wu ◽  
K.K Yeo ◽  
S.Y.A Lee ◽  
J.S Hon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Missing Values ◽  
Warfarin Dose ◽  
Learning Model ◽  
Training Data ◽  
Multiple Drug ◽  
Data Set ◽  
Machine Learning Model ◽  
Data Points ◽  
Test Sets

Abstract Background Warfarin titration via International Normalised Ratio (INR) monitoring can be a challenge for patients on long term anticoagulation due to its multiple drug interactions, long half life and patient's individual reponse, yet critically important due to its narrow therapeutic index. Machine learning may have a role in learning and replicating existing warfarin prescribing practices, to be potentially incorporated into an automated warfarin titration model. Purpose We aim to explore the feasibility of using machine learning to develop a model that can learn and predict actual warfarin titration practices. Methods A retrospective dataset of 4,247 patients with 48,895 data points of INR values were obtained from our institutional database. Patients who had less than 5 visits recorded, invalid or missing values were excluded. Variables studied included age, warfarin indication, warfarin dose, target INR range, actual INR values, time between titration and time in therapeutic range (TTR as defined by the Rosenthal formula). The machine learning model was developed on an unbiased training data set (1,805 patients), further refined on a handpicked balanced validation set (400 patients), before being evaluated on two balanced test sets of 100 patients each. The test sets were handpicked based on the criteria of TTR (“in vs out of range”) and stability of INR results (“low vs high fluctuation”) (Table 1). Given the time series nature of the data, a Recurrent Neural Network (RNN) was chosen to learn warfarin prescription practices. Long-short term memory (LSTM) cells were further employed to address the problem of time gaps between warfarin titration visits which could result in vanishing gradients. Results A total of 2,163 patients with 42,622 data points were studied (mean age 65±11.7 years, 54.7% male). The mean TTR was 65.4%. The total warfarin dose per week as predicted by the RNN was compared with actual total warfarin dose per week prescribed for each patient in the test sets. The coefficient of determination for the RNN in the “in vs out of range” and “low vs high fluctuation” test sets were 0.941 and 0.962 respectively (Figure 1). Conclusion This proof of concept study demonstrated that a RNN based machine learning model was able to learn and predict warfarin dosage changes with reasonable accuracy. The findings merit further evaluation of the potential use of machine learning in an automated warfarin titration model. Funding Acknowledgement Type of funding source: None

scholarly journals Data Pre-Processing for Machine Learning Models using Python Libraries

2020 ◽  
Vol 9 (4) ◽  
pp. 1995-1999
Keyword(s):  
Machine Learning ◽  
Missing Values ◽  
Model Fitting ◽  
Learning Model ◽  
Data Sets ◽  
Data Set ◽  
Machine Learning Model ◽  
Level Data ◽  
Efficient Machine ◽  
High Level

Data pre-processing is the process of transforming the raw data into useful dataset. Data pre-processing is one of the most important phase of any machine learning model because the quality and efficiency of any machine learning model directly depends upon the data-set, if we skip this step and design a model with data sets containing missing values then the model we have designed will not be that efficient and will be inconsistent model. This paper describes the methodology for pre-processing the data in seven sequence of steps using python powerful libraries which are open source machine learning libraries that support both supervised and unsupervised learning like pandas is a high level data manipulation tool, scikit learn which provides various tools for model fitting, data pre-processing, model selection and many other utilities. These steps include dealing with missing value, categorical values, importing data sets etc. This analysis helps in cleaning and transforming the datasets which future applied to any learning model and produce a efficient machine learning model.

scholarly journals Auditor Choice Prediction Model Using Corporate Governance and Ownership Attributes: Machine Learning Approach

2021 ◽  
Vol 11 (7) ◽  
pp. 1-7
Author(s):  
Rahayu Abdul Rahman ◽  
◽  
Suraya Masrom ◽  
Nor Balkish Zakaria ◽  
Sunarti Halid
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Financial Reporting ◽  
Learning Algorithm ◽  
Stock Exchange ◽  
Features Selection ◽  
Firm Characteristics ◽  
Auditor Choice ◽  
Machine Learning Model ◽  
Bayes Algorithm

t-External auditor is one of the governance mechanisms in mitigating corporate managerial misconduct and thereby enhance the credibility of accounting information. Thus, the main objective of this study is to develop machine learning prediction model on auditor choice of the firm which signal the quality of auditing and financial reporting processes.This paper presents the fundamental knowledge on the design and implementation of machine learning model based on four selected algorithms tested on the real dataset of 2,262 firm-year observations of companies listed on Malaysian stock exchange from 2000 to 2007. The performance of each machine learning algorithm on the auditor choice dataset has been observed based on three groups of features selection namely firm characteristics, governance and ownership. The findings indicated that the machine learning models present better accuracy performance with ownership features selection mainly with the Naïve Bayes algorithm. Keywords-Auditor Choice, Machine Learning, Prediction, Malaysia

Sign in / Sign up

Export Citation Format

Share Document