Customer Churn in Retail E-Commerce Business: Spatial and Machine Learning Approach

This study is a comprehensive and modern approach to predict customer churn in the example of an e-commerce retail store operating in Brazil. Our approach consists of three stages in which we combine and use three different datasets: numerical data on orders, textual after-purchase reviews and socio-geo-demographic data from the census. At the pre-processing stage, we find topics from text reviews using Latent Dirichlet Allocation, Dirichlet Multinomial Mixture and Gibbs sampling. In the spatial analysis, we apply DBSCAN to get rural/urban locations and analyse neighbourhoods of customers located with zip codes. At the modelling stage, we apply machine learning extreme gradient boosting and logistic regression. The quality of models is verified with area-under-curve and lift metrics. Explainable artificial intelligence represented with a permutation-based variable importance and a partial dependence profile help to discover the determinants of churn. We show that customers’ propensity to churn depends on: (i) payment value for the first order, number of items bought and shipping cost; (ii) categories of the products bought; (iii) demographic environment of the customer; and (iv) customer location. At the same time, customers’ propensity to churn is not influenced by: (i) population density in the customer’s area and division into rural and urban areas; (ii) quantitative review of the first purchase; and (iii) qualitative review summarised as a topic.

Vietnamese Learners’ Performance in The IELTS Writing Task 2

IELTS is popular in Vietnam thanks to its reliability and applicability. Writing task 2 has been acknowledged to be the most challenging for IELTS learners. However, in Vietnam, not much research has attempted to investigate in an in-depth manner as to what are the problems, causes, and consequently the suggestions of such a notion. The research hence aims to investigate the phenomenon in a more thorough, empirical manner. To this end, the study employed the participation of 205 IELTS learners from two language centers in Ho Chi Minh city to provide their opinions regarding the problems, causes, and recommendations deemed the most pressing, acute, and beneficial, respectively. With convenience sampling and survey being the chosen research design, the research was quantitative in nature, producing numerical data as a result. Further analysis conducted via comparing the means of the items listed in the questionnaire yielded based on the IELTS band descriptors managed to discover a series of problems, causes, and suggestions considered the most relevant to the Vietnamese learners concerning IELTS writing task 2. The research thus served as the basis for teachers and learners of IELTS writing task 2 to identify the recurrent issues and provide relatable approaches.

Recurrent Multinomial Models for Categorical Sequences

This paper presents a model of recurrent multinomial sequences. Though there exists a quite considerable literature on modeling autocorrelation in numerical data and sequences of categorical outcomes, there is currently no systematic method of modeling patterns of recurrence in categorical sequences. This paper develops a means of discovering recurrent patterns by employing a more restrictive Markov assumption. The resulting model, which I call the recurrent multinomial model, provides a parsimonious representation of recurrent sequences, enabling the investigation of recurrences on longer time scales than existing models. The utility of recurrent multinomial models is demonstrated by applying them to the case of conversational turn-taking in meetings of the Federal Open Market Committee (FOMC). Analyses are effectively able to discover norms around turn-reclaiming, participation, and suppression and to evaluate how these norms vary throughout the course of the meeting.

A Water Surface Contaminants Monitoring Method Based on Airborne Depth Reasoning

Water surface plastic pollution turns out to be a global issue, having aroused rising attention worldwide. How to monitor water surface plastic waste in real time and accurately collect and analyze the relevant numerical data has become a hotspot in water environment research. (1) Background: Over the past few years, unmanned aerial vehicles (UAVs) have been progressively adopted to conduct studies on the monitoring of water surface plastic waste. On the whole, the monitored data are stored in the UAVS to be subsequently retrieved and analyzed, thereby probably causing the loss of real-time information and hindering the whole monitoring process from being fully automated. (2) Methods: An investigation was conducted on the relationship, function and relevant mechanism between various types of plastic waste in the water surface system. On that basis, this study built a deep learning-based lightweight water surface plastic waste detection model, which was capable of automatically detecting and locating different water surface plastic waste. Moreover, a UAV platform-based edge computing architecture was built. (3) Results: The delay of return task data and UAV energy consumption were effectively reduced, and computing and network resources were optimally allocated. (4) Conclusions: The UAV platform based on airborne depth reasoning is expected to be the mainstream means of water environment monitoring in the future.

Numerical framework for unsteady bioconvection flow of third-grade nanofluid over a porous Riga surface with convective Nield approach

The ultra-high significances of thermal radiation, magnetic field and activation energy in thermal enhancement processes allow significant applications in chemical and mechanical engineering, modern technology and various thermal engineering eras. The improvement in energy resources and production became one of the major challenges for researchers and scientists for sustained development in industrial growths. Beside this, the bioconvection assessment in nanomaterials conveys prestigious applications in biotechnology like bio-sensors, enzymes, petroleum industry, bio-fuels and many more. In view of such renewable applications, present exploration discloses unsteady two-dimensional flow of third-grade nanomaterial accommodating gyrotactic microorganisms induced by unsteady stretched Riga sheet in porous medium. The formulated flow problem is further scrutinized by utilizing the chemical reaction, activation energy, thermal radiation and magnetic aspects. The convective Nield constraints are further subjected in the current investigation. Apposite transformations are used to condense the nonlinear developed problem into dimensionless ordinary form. The numerical solution of such similar flow problem is presented via shooting technique. The detailed graphical illustrations of the dimensionless temperature, nanoparticles concentration, velocity and motile microorganisms for physical significance of diverse relevant parameters are deliberated. Furthermore, numerical data of local Sherwood, Nusselt and motile density numbers is designated in tabular form. Study accentuated that velocity increases for higher modified Hartmann and material constants, while the effects of buoyancy ratio and bioconvected Rayleigh numbers are rather opposite. The temperature, microorganism and concentration distributions were enhanced for unsteady parameter. It is also acknowledged that the concentration distribution is enhanced for activating the energy number. Moreover, the microorganism distribution enhances for concentration difference and magneto-porous constants, while bioconvected Lewis and Peclet numbers show conflicting trend.

Mechanics of Materials Natural Fibers Technology on Thermal Properties of Polymer

The thermal characteristics of polymathic methacrylate combined with unsaturated polyester were determined by numerical and experimental research. Models for numerically investigating the parameters of thermal conductivity, specific heat capacity, and thermal diffusivity were developed using COMSOL Multiphysics. The numerical data were then compared to experimental results for the same material using the same measurements to ensure that they were correct. By comparing the thermal conductivity data to two sets of theoretical data, the results were confirmed. The COMSOL models were quite close to the experimental data, with just minor differences between the three models. One set of theoretical data coincided with the mean of the other data, while the second set revealed a significant departure below the other data.

Impact of industry on agricultural development in Sylhet region of Bangladesh: Farmer’s perception

The study targets at farmer’s perception and their cognition how they conceive that agricultural performance has been affected and devastated through industrial work. It reviews and investigates the opinion of 25% farmers of two villages from each upazila of two named Madhapur and Habiganj sadar upazila in Sylhet division where Charu Ceramic Industry Limited and Olipur industry are located respectively from mid-September to mid-October, 2021 through survey of questionnaire, interview and group discussion. According to 85% farmers, the industry shades agriculture by imposing an adverse and toxic impact on agricultural exposure and development. Among them, (41.6% and 48.4%) of farmers realize that the industry creates high propensity of losing standard quality of soil and water, respectively. They (40.2%) notice that invasion of several dangerous insects on crops has become prominent and unmanageable near the industrial area. The study represents such kind of realization of farmers to show a salient feature in view of their finding causes and intuition with significant numerical data. Int. J. Agril. Res. Innov. Tech. 11(2): 133-138, Dec 2021

Design of a Food Recommendation System using ADNet algorithm on a Hybrid Data Mining Process

Hybrid data mining processes are employed in recent days on several applications to achieve a better prediction and classification rate along with customer satisfaction. Hybrid data mining processes are the combination of different form of data considered for a neural network decision. In some cases, the different form of data represents image along with numerical data. In the proposed work, a food recommendation system is developed with respect to the flavour taste of the customer and considering the review comments of previous customers. The suggestions given by the users are taken into account as a feedback layer in the neural network for fine tuning the accuracy of the prediction process. The architectural design of the proposed model is employed with an ADNet (Adaptively Dense Convolutional Neural Network) algorithm to enable the usage of low range features in an efficient way. To verify the performance of the developed model, a pizza flavour recommender dataset is employed in the work for analysis. The experimental work analysis indicates that the ADNet algorithm works in a better way on a hybrid data analysis than the traditional DenseNet and ResNet algorithms.