To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Using Machine Learning Technique for Analytical Customer Loyalty |
|
Author |
Mohamed M. Abbassy |
| Citation |
Vol. 25 No. 8 pp. 113-121 |
|
Abstract |
To enhance customer satisfaction for higher profits, an e-commerce sector can establish a continuous relationship and acquire new customers. Utilize machine-learning models to analyse their customer's behavioural evidence to produce their competitive advantage to the e-commerce platform by helping to improve overall satisfaction. These models will forecast customers who will churn and churn causes. Forecasts are used to build unique business strategies and services offers. This work is intended to develop a machine-learning model that can accurately forecast retainable customers of the entire e-commerce customer data. Developing predictive models classifying different imbalanced data effectively is a major challenge in collected data and machine learning algorithms. Build a machine learning model for solving class imbalance and forecast customers. The satisfaction accuracy is used for this research as evaluation metrics. This paper aims to enable to evaluate the use of different machine learning models utilized to forecast satisfaction. For this research paper are selected three analytical methods come from various classifications of learning. Classifier Selection, the efficiency of various classifiers like Random Forest, Logistic Regression, SVM, and Gradient Boosting Algorithm. Models have been used for a dataset of 8000 records of e-commerce websites and apps. Results indicate the best accuracy in determining satisfaction class with both gradient-boosting algorithm classifications. The results showed maximum accuracy compared to other algorithms, including Gradient Boosting Algorithm, Support Vector Machine Algorithm, Random Forest Algorithm, and logistic regression Algorithm. The best model developed for this paper to forecast satisfaction customers and accuracy achieve 88 %. |
|
Keywords |
Satisfaction forecasting, Churn forecasting, Machine Learning, e-commerce. |
|
URL |
|
|
Title |
Investigation into Changing of Geometry and Boundary Conditions of Stepped Premixed Micro-Combustor |
|
Author |
Mohammad Hadi Jal and Ali Reza Rahbari |
| Citation |
Vol. 25 No. 8 pp. 113-123 |
|
Abstract |
In the present study a micro-combustor having the geometry of a hollow cylinder is investigated, in which the combustor diameter in the entrance is less than its main part that is actually a stepped-form combustor and methane-air combustion is occurred within the chamber and the investigation is undertaken by solving 2D governing equations. In order to determine the effect of elongation of the entrance part and increase in the chamber diameter, a geometry with an inlet diameter of Din=1 mm, inlet length of Lin=7 mm and a main diameter of D=2 mm as a reference case was compared with two geometries one with an inlet diameter of Din=1 mm, an inlet length of Lin=10 mm and a main diameter of D=2 mm and the other having inlet diameter of Din=1.5 mm, inlet length of Lin=7 mm and a main diameter of D=3 mm. All of them had the same total length and they were compared for inlet velocities of u=3 m/s, 2 m/s, and 1.5 m/s. The centerline temperature, the wall temperature, and the radiation efficiency are of the results more investigated in this study. In a constant geometry, increasing of the inlet velocity causes the flame temperature to increase, though slightly. Moreover, it leads to move the flame downstream. This increase has a more influence on the wall temperature and makes it rise to a higher level along the combustor in the inlet velocity of u=3 m/s. It was concluded that in a constant velocity, increasing of inlet length only makes delay in the flame formation and does not affects the flame temperature, significantly. Finally, it was shown that in the geometry with less inlet diameter and length, the radiation efficiency is placed at a higher level in comparison to the geometry with larger inlet diameter and length at all velocities. In addition, it was observed that increase in the inlet velocity leads to reduce the efficiency in all the three geometries and this reduction is more intense and with steeper slope for the geometry having larger diameter. In addition to the lack of research conducted on methane combustion in the geometries studied, the difference between the present study and others in this area is that the simultaneous effects of geometry and velocity on combustion parameters are studied in more details and also, it is used from a different combustion mechanism as compared to other studies |
|
Keywords |
Micro-combustor, Radiation Efficiency, Flame Temperature |
|
URL |
