Using Machine Learning Methods to Solve Problems of Forecasting Demand for New Products in the Internet Marketplace

2020 ◽  
Vol 10 (4) ◽  
pp. 41-50
Author(s):  
A.A. Osin ◽  
A.K. Fomin ◽  
G.B. Sologub ◽  
V.I. Vinogradov
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
New Products ◽  
The Internet ◽  
Specific Task ◽  
Learning Methods ◽  
Online Store ◽  
Machine Learning Methods ◽  
And Storage ◽  
Internet Marketplace

The work is aimed at researching the possibility of using machine learning methods to build models for forecasting demand for new products in the online store Ozon. ru. Approaches to the solution that were not previously used in a specific task are proposed for consideration. Data on sales history and storage of goods at Ozon.ru are used as a sample. There is a description and analysis of the approximate loss of the Ozon.ru website, the data used, the process of building a base model, and the results obtained. It describes the metrics used to evaluate the prediction results and makes a comparative analysis between the prediction results of the built model and the results of heuristically selected values.

scholarly journals Using Machine Learning Methods to Solve Problems of Forecasting the Amount and Probability of Purchase Based on E-Commerce Data

2020 ◽  
Vol 10 (4) ◽  
pp. 31-40
Author(s):  
O.A. Mamiev ◽  
N.A. Finogenov ◽  
G.B. Sologub
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Accurate Estimate ◽  
Gradient Boosting ◽  
Learning Methods ◽  
Online Store ◽  
Machine Learning Methods

The study is aimed at investigating the possibility of using machine learning methods to build models for predicting the probability of purchase and the amount of purchase by online store customers. As a sample, we used data of users transactions of the site ponpare.jp in the period from 01.07.2011 to 23.06.2012. The description and comparative analysis of the most common methods for solving similar problems are given. The metrics used to measure the results in the case of forecasting the fact and amount of the purchase are being described. The results obtained make it clear that within the framework of the problem of predicting the probability of a purchase, gradient boosting, namely its implementation of LGBMClassifier, shows the most accurate estimate. For the problem of predicting the amount of a customer’s purchase, using gradient boosting also gave the best results.

scholarly journals PREDICTING TIME BEFORE THE NEXT ORDER IN THE ONLINE STORE, BASED ON MACHINE LEARNING METHODS

2020 ◽  
Author(s):  
Olena Piskunova ◽  
◽  
Rostyslav Klochko ◽  
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Random Forest ◽  
Rapid Development ◽  
Confusion Matrix ◽  
Individual Characteristics ◽  
Support Vector ◽  
Learning Methods ◽  
Online Store ◽  
Machine Learning Methods

Due to the rapid development of e-commerce and increased competition in the retail market of Ukraine, companies are forced to look for new ways to grow their business. One of the options is to optimize business processes, in particular to increase the efficiency of marketing activities. Predicting consumer behavior is one of the most effective methods of optimizing marketing budgets by building processes based on the individual characteristics of each client. The aim of the study was to predict the behavior of online store customers, namely the time before the next order, based on machine learning methods and a comparative analysis of the effectiveness of different modeling algorithms. Five classification algorithms were implemented: linear discriminant analysis, сlassification and regression trees, random forest, support vector machine, k - nearest neighbors and comparative analysis of their efficiency was performed. Given the peculiarities of customer behavior for forecasting time to the next order, it is proposed to consider the following time intervals in the future when the customer makes the next order: up to two months, two to six months, six to fifteen months, and without order. Predicting such intervals allows us to identify customers who are more likely to make the next purchase and focus our advertising budgets on them, or build a customer experience management strategy: activate customers who have left, offer discounts to customers who are going to leave. Peculiarities of classification models quality assessment on the basis of the “confusion matrix” according to the forecasting accuracy indicators “Accuracy”, “F1”, “Recall” and “Precision” is considered. The study allowed us to give preference to the model of classification "random forest". A tenfold cross-validation was used to improve the quality of the simulation. The weighted accuracy of “F1” in the groups “Up to two months” and “two-six months” reached 62.5% and 64.1%, respectively. The developed model should reduce the influence of the human factor on the decision-making process in the construction of marketing strategies.

scholarly journals Implementation of ML Algorithm’s for Cyber Security

2021 ◽  
pp. 54-61
Author(s):  
Mohammad Asif ◽  
Prof. E. M. Chirchi
Keyword(s):  
Machine Learning ◽  
Cyber Security ◽  
The Internet ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
System Movement

Machine learning is embraced in an extensive variety of areas where it demonstrates its predominance over customary lead based calculations. These strategies are being coordinated in digital recognition frameworks with the objective of supporting or notwithstanding supplanting the principal level of security experts although the total mechanization of identification and examination is a luring objective, the adequacy of machine learning in digital security must be assessed with the due steadiness. With the improvement of the Internet, digital assaults are changing quickly and the digital security circumstance isn't hopeful. Since information are so critical in ML/DL strategies, we portray a portion of the normally utilized system datasets utilized in ML/DL, examine the difficulties of utilizing ML/DL for digital security and give recommendations to look into bearings. Malware has developed over the previous decades including novel engendering vectors, strong versatility methods and different and progressively propelled assault procedures. The most recent manifestation of malware is the infamous bot malware that furnish the aggressor with the capacity to remotely control traded off machines therefore making them a piece of systems of bargained machines otherwise called botnets. Bot malware depend on the Internet for proliferation, speaking with the remote assailant and executing assorted noxious exercises. As system movement, action is one of the principle characteristics of malware and botnet task, activity investigation is frequently observed as one of the key methods for recognizing traded off machines inside the system. We present an examination, routed to security experts, of machine learning methods connected to the recognition of interruption, malware, and spam.

Comparative analysis of feature representations and machine learning methods in Android family classification

2021 ◽  
Vol 184 ◽  
pp. 107639
Author(s):  
Yude Bai ◽  
Zhenchang Xing ◽  
Duoyuan Ma ◽  
Xiaohong Li ◽  
Zhiyong Feng
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Learning Methods ◽  
Feature Representations ◽  
Machine Learning Methods ◽  
Family Classification

scholarly journals Social Media Analytics of the Internet of Things

2021 ◽  
Author(s):  
Jim Scheibmeir ◽  
Yashwant K. Malaiya
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Internet Of Things ◽  
Smart Cities ◽  
The Internet ◽  
Social Media Analytics ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Internet Of Things Technology ◽  
The Internet Of Things

Abstract The Internet of Things technology offers convenience and innovation in areas such as smart homes and smart cities. Internet of Things solutions require careful management of devices and the risk mitigation of potential vulnerabilities within cyber-physical systems. The Internet of Things concept, its implementations, and applications are frequently discussed on social media platforms. This article illuminates the public view of the Internet of Things through a content-based analysis of contemporary conversations occurring on the Twitter platform. Tweets can be analyzed with machine learning methods to converge the volume and variety of conversations into predictive and descriptive models. We have reviewed 684,503 tweets collected in a two-week period. Using supervised and unsupervised machine learning methods, we have identified interconnecting relationships between trending themes and the most mentioned industries. We have identified characteristics of language sentiment which can help to predict popularity within the realm of IoT conversation. We found the healthcare industry as the leading use case industry for IoT implementations. This is not surprising as the current Covid-19 pandemic is driving significant social media discussions. There was an alarming dearth of conversations towards cybersecurity. Only 12% of the tweets relating to the Internet of Things contained any mention of topics such as encryption, vulnerabilities, or risk, among other cybersecurity-related terms.

Sign in / Sign up

Export Citation Format

Share Document