scholarly journals Context-Specific Point-of-Interest Recommendation Based on Popularity-Weighted Random Sampling and Factorization Machine

2021 ◽  
Vol 10 (4) ◽  
pp. 258
Author(s):  
Dongjin Yu ◽  
Yi Shen ◽  
Kaihui Xu ◽  
Yihang Xu
Keyword(s):  
Random Sampling ◽  
Sampling Method ◽  
Specific Point ◽  
Point Of Interest ◽  
Poi Recommendation ◽  
Bayesian Personalized Ranking ◽  
Location Based Social Network ◽  
Factorization Machine ◽  
Context Specific ◽  
Potential Customers

Point-Of-Interest (POI) recommendation not only assists users to find their preferred places, but also helps businesses to attract potential customers. Recent studies have proposed many approaches to the POI recommendation. However, the lack of negative samples and the complexities of check-in contexts limit their effectiveness significantly. This paper focuses on the problem of context-specific POI recommendation based on the check-in behaviors recorded by Location-Based Social Network (LBSN) services, which aims at recommending a list of POIs for a user to visit at a given context (such as time and weather). Specifically, a bidirectional influence correlativity metric is proposed to measure the semantic feature of user check-in behavior, and a contextual smoothing method to effectively alleviate the problem of data sparsity. In addition, the check-in probability is computed based on the geographical distance between the user’s home and the POI. Furthermore, to handle the problem of no negative feedback in LBSN, a weighted random sampling method is proposed based on contextual popularity. Finally, the recommendation results is obtained by utilizing Factorization Machine with Bayesian Personalized Ranking (BPR) loss. Experiments on a real dataset collected from Foursquare show that the proposed approach has better performance than others.

scholarly journals Category-aware Next Point-of-Interest Recommendation via Listwise Bayesian Personalized Ranking

2017 ◽  
Author(s):  
Jing He ◽  
Xin Li ◽  
Lejian Liao
Keyword(s):  
Ranking List ◽  
Point Of Interest ◽  
Spatial Influence ◽  
Poi Recommendation ◽  
Bayesian Personalized Ranking ◽  
Real World Datasets ◽  
Location Based Social Networks ◽  
Luce Model ◽  
Personalized Ranking ◽  
High Computational Complexity

Next Point-of-interest (POI) recommendation has become an important task for location-based social networks (LBSNs). However, previous efforts suffer from the high computational complexity and the transition pattern between POIs has not been well studied. In this paper, we propose a two-fold approach for next POI recommendation. First, the preferred next category is predicted by using a third-rank tensor optimized by a Listwise Bayesian Personalized Ranking (LBPR) approach. Specifically we introduce two functions, namely Plackett-Luce model and cross entropy, to generate the likelihood of ranking list for posterior computation. Then POI candidates filtered by the predicated category are ranked based on the spatial influence and category ranking influence. Extensive experiments on two real-world datasets demonstrate the significant improvements of our methods over several state-of-the-art methods.

scholarly journals POI Recommendation Method Using Deep Learning in Location-Based Social Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yang Liu ◽  
An-bo Wu
Keyword(s):  
Social Networks ◽  
Deep Learning ◽  
Short Term Memory ◽  
Large Data ◽  
Short Term ◽  
Point Of Interest ◽  
Poi Recommendation ◽  
Bayesian Personalized Ranking ◽  
Location Based Social Networks ◽  
Current Sequence

To solve the problems of large data sparsity and lack of negative samples in most point of interest (POI) recommendation methods, a POI recommendation method based on deep learning in location-based social networks is proposed. Firstly, a bidirectional long-short-term memory (Bi-LSTM) attention mechanism is designed to give different weights to different parts of the current sequence according to users’ long-term and short-term preferences. Then, the POI recommendation model is constructed, the sequence state data of the encoder is input into Bi-LSTM-Attention to get the attention representation of the current POI check-in sequence, and the Top- N recommendation list is generated after the decoder processing. Finally, a negative sampling method is proposed to obtain an effective negative sample set, which is used to improve the calculation of the Bayesian personalized ranking loss function. The proposed method is demonstrated experimentally on Foursquare and Gowalla datasets. The experimental results show that the proposed method has better accuracy, recall, and F1 value than other comparison methods.

Faktor-Faktor Yang Mempengaruhi Keputusan Mahasiswa Memilih Program Studi Kebidanan STIKES Muhammadiyah Ciamis Tahun 2016

2018 ◽  
Vol 5 (1) ◽  
pp. 69-82
Author(s):  
Evi Mariana
Keyword(s):  
Data Analysis ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Random Sampling ◽  
Sampling Method ◽  
Marketing Mix ◽  
Stratified Random Sampling ◽  
Price Promotion ◽  
F Test ◽  
Physical Evidence

The purpose of this study was to analyze the factors that influence the decisionof the students chose to study in Obstetrics Prodi STIKES Muhammadiyah Ciamis and analyze the factors that most influence the decision of the students chose to study in Obstetrics Prodi STIKES Muhammadiyah Ciamis. Collecting data in this study was conducted using a survey by questionnaire to 114 students by stratified random sampling method. Methods of data analysis using multiple linear regression, F test and test T. The result is a marketing mix that significantly is the product, place, and physical evidence. And that does not affect the marketing mix is price, promotion, place, and processes

BANKACILIKTA MÜŞTERİ İLİŞKİLERİ YÖNETİMİNİN MÜŞTERİ SADAKATİNE ETKİSİ

2015 ◽  
Vol 3 (1) ◽  
Author(s):  
Fikret GÜMÜŞBUĞA
Keyword(s):  
Customer Loyalty ◽  
Random Sampling ◽  
Management System ◽  
Care Management ◽  
Sampling Method ◽  
Simple Random Sampling ◽  
Face To Face ◽  
Descriptive Research ◽  
Customer Care ◽  
Research Type

This study mainly focuses on customer care management and customer loyalty. Even though there are many experiential studies about customer care management and customer loyalty system, the lack of studies on customers in Karabük and Safranbolu locally, has leaded to focus on this study. Thus, this study mainly focuses on the influence of customer care treatments of banks in Karabük and Safranbolu on customer loyalty. Descriptive research type was used in the study. In this study simple random sampling method was used which is one of the probability sampling method, face to face surwey to all 726 participants was used for the study. As the result of the experiential study, the attendance and influence of customer care management and loyalty systems have been comparatively low, but it has been figured out that customer care management system influences customer loyalty level.

A Scale Development Approach To Employees’ Perspective Of Knowledge Management In Banks

2019 ◽  
Vol 118 (7) ◽  
pp. 82-94
Author(s):  
DR.C. KATHIRAVAN ◽  
DR.M. MANIVANNAN ◽  
E.CHANDRA MOULI ◽  
A. RAJASEKAR
Keyword(s):  
Knowledge Management ◽  
Random Sampling ◽  
Tamil Nadu ◽  
Sampling Method ◽  
Sampling Technique ◽  
Technology Knowledge ◽  
Interview Method ◽  
Development Approach ◽  
Chennai City ◽  
Future Topics

The data were collected using personal interview method and a total of 455 employees who were in some aspect knowledge management in banks and identified through multistage random sampling method. Multistage random sampling technique is a probability sampling type where available study topics employ future topics from among their contacts. The study was limited to Chennai city of Tamil Nadu. The analysis found that banks employees moderately perceived towards factors of knowledge management such as knowledge utilization, information technology, knowledge motivation, knowledge storage, knowledge sharing enablers and knowledge creation. Hence, it is concluded that training program is important for the survival of knowledge management. It is also imperative for effective of employees’ job performance.

Kapasitas Adaptasi dan Resiliensi Komunitas Menghadapi Bencana Erupsi Gunung Merapi

2019 ◽  
Vol 2 (5) ◽  
pp. 617
Author(s):  
Nyimas Ayu Dillashandy ◽  
Nurmala K Panjaitan
Keyword(s):  
Adaptive Capacity ◽  
Random Sampling ◽  
Qualitative Data ◽  
Sampling Method ◽  
Sampling Technique ◽  
Community Resilience ◽  
Simple Random Sampling ◽  
Quantitative Approach ◽  
Institutional Memory ◽  
Innovative Learning

Mount Merapi eruption has occurred several times in Indonesia and the biggest eruption that last occurred in 2010. The community were suffered losses and were affected by eruptions. The purposes of this research are to analyze community resilience, to analyze the level of vulnerability, and to analize the community adaptive capacity. The research using a quantitative approach supported by qualitative data. Simple random sampling technique is used as the sampling method and the informant was taken purposively. The results of this research showed that when the eruption occurred the community has a high vulnerability. The adaptive capacity is also high with innovative learning based on institutional memory and supported by the connectedness. Communities achieve resilience and can adapt to changes with high adaptive capacity.  Keywords: adaptive capacity, community resilience, eruption, vulnerability ABSTRAK Erupsi Gunung Merapi sudah terjadi beberapa kali di Indonesia dan erupsi terbesar yang terjadi terakhir kalinya yaitu pada tahun 2010. Komunitas mengalami berbagai kerugian dan terkena dampak dari erupsi. Tujuan dari penelitian ini adalah untuk menganalisis resiliensi komunitas, menganalisis tingkat kerentanan komunitas, dan menganalisis kapasitas adaptasi komunitas. Penelitian ini dilaksanakan dengan menggunakan pendekatan kuantitatif yang didukung oleh data kualitatif. Pemilihan responden dilakukan dengan teknik sampel acak sederhana sedangkan pemilihan terhadap informan dilakukan secara sengaja. Hasil penelitian ini menunjukkan bahwa saat erupsi terjadi komunitas memiliki kerentanan yang tinggi. Kapasitas adaptasi komunitas tinggi dengan adanya innovative learning yang didasari oleh pengetahuan dan pengalaman dan didukung oleh jaringan yang dimiliki. Komunitas berhasil mencapai resiliensi dan dapat beradaptasi dengan perubahan-perubahan dengan kapasitas adaptasi yang tinggi.Kata kunci : kapasitas adaptasi, kerentanan, erupsi, resiliensi komunitas

PENGARUH NILAI PELANGGAN, INOVASI PRODUK DAN KUALITAS LAYANAN TERHADAP LOYALITAS NASABAH BANK MUAMALAT INDONESIA CABANG MADIUN

2018 ◽  
Vol 1 (1) ◽  
Author(s):  
Binti Mutafarida
Keyword(s):  
Quality Of Service ◽  
Customer Loyalty ◽  
Random Sampling ◽  
Product Innovation ◽  
Customer Value ◽  
Research Method ◽  
Sampling Method ◽  
Descriptive Research ◽  
Independent Variable

The development of sharia banking in Indonesia very rapidly grow up preceded by Bank Muamalat Indonesia and in 2013 ranked as the bank with the highest loyalty and the best among other sharia banking nationally. Bank Muamalat Indonesia branch of Madiun is one of the first branch in Madiun and currently has many competitors from other sharia banking. Based on this background, in this study take what factors affect the size of customer loyalty Bank Muamalat Indonesia branch of Madiun. Based on the result of research, it is found that the level of loyalty of customer of Bank Muamalat of Madiun branch is mostly influenced by product innovation with value of t test value obtained by t-count 2,493, while second factor is influenced by service quality with result of tcount 2,268. So the least influenced factor by the value of the customer is with value of 2.217. This research is a descriptive research method and associative / relationship, this matter to know the value of independent variable. While population of this research is funding customer of Bank Muamalat Indonesia branch of Madiun with amount of 22.196 customer by taking data using random sampling method as much as 108 customer. Keyword: Customer Value, Product Innovation AND Quality Of Service

Pengaruh Motivasi Kerja dan Budaya Kerja Terhadap Produktivitas Kerja Karyawan di Kebun Huta Padang PT. Perkebunan Nusantara III (PERSERO) Kabupaten Asahan Sumatera Utara

2020 ◽  
Vol 2 (2) ◽  
pp. 167-180
Author(s):  
Luli Achmad Gozali ◽  
Yusniar Lubis ◽  
Syaifuddin Syaifuddin
Keyword(s):  
Linear Regression ◽  
Data Collection ◽  
Multiple Linear Regression ◽  
Random Sampling ◽  
Research Method ◽  
Sampling Method ◽  
Quantitative Approach ◽  
Stratified Random Sampling ◽  
Direct Influence ◽  
Dominant Influence

This study is aimed to determine and analyze the effect of the implementation of motivation and culture on the employees productivity at Huta Padang estate of PT. Perkebunan Nusantara III (Persero) Asahan Regency North Sumatera. This research method uses a quantitative approach, the type of research is a survey. The sample was determined by stratified random sampling method, 95 people. The data collection through questionnaires. Data were analyzed using multiple linear regression. The results showed that partially and simultaneously, the implementation of motivation and culture had a positive and significant effect on the employess productivity at Huta padang estate of PT. Perkebunan Nusantara III (Persero) Asahan Regency North Sumatera. The determination coefficient value of 0.882, indicates that the influence of the implementation of motivation and culture on the employess productivity of Huta Padang estate of PT. Perkebunan Nusantara III (Persero) Asahan Regency North Sumatera is 88.2%. The culture has more dominant influence on the employees produktivity at  Huta Padang estate of PT. Perkebunan Nusantara III (Persero) Asahan Regency North Sumatera, with a direct influence of 73,2%. 

scholarly journals Feature-Weighted Sampling for Proper Evaluation of Classification Models

2021 ◽  
Vol 11 (5) ◽  
pp. 2039
Author(s):  
Hyunseok Shin ◽  
Sejong Oh
Keyword(s):  
Random Sampling ◽  
Sampling Method ◽  
Classification Model ◽  
Training Set ◽  
Test Set ◽  
Feature Importance ◽  
Proper Training ◽  
Machine Learning Applications ◽  
Test Sets ◽  
The Given

In machine learning applications, classification schemes have been widely used for prediction tasks. Typically, to develop a prediction model, the given dataset is divided into training and test sets; the training set is used to build the model and the test set is used to evaluate the model. Furthermore, random sampling is traditionally used to divide datasets. The problem, however, is that the performance of the model is evaluated differently depending on how we divide the training and test sets. Therefore, in this study, we proposed an improved sampling method for the accurate evaluation of a classification model. We first generated numerous candidate cases of train/test sets using the R-value-based sampling method. We evaluated the similarity of distributions of the candidate cases with the whole dataset, and the case with the smallest distribution–difference was selected as the final train/test set. Histograms and feature importance were used to evaluate the similarity of distributions. The proposed method produces more proper training and test sets than previous sampling methods, including random and non-random sampling.

scholarly journals Investigating the Relationship between Professionalism and (Technical, Human, and Perceptual) Skills of Managers in Poly Akril Company of Iran from Experts’ Viewpoint

2016 ◽  
Vol 6 (2) ◽  
pp. 117
Author(s):  
Marzie Ghanbari ◽  
Reza Hoveida ◽  
Seyed Ali Siadat
Keyword(s):  
Data Collection ◽  
Random Sampling ◽  
Sampling Method ◽  
Regression Coefficient ◽  
Reliability Coefficient ◽  
Descriptive Statistics ◽  
Stratified Random Sampling ◽  
Perceptual Skills ◽  
The Relationship ◽  
Test Correlation

The objective of the present study is to investigate the relationship between managers’ professionalism and (technical, human, and perceptual) skills in managers of Iran Poly Akril Company. The research is an applied one in terms of objectives, and a descriptive-correlational in terms of method. The population includes all experts working in the company in 2012 as 240 individuals among who 144 participants were selected using the stratified random sampling method proportionate to the population size as the sample size. The data collection instruments were two researcher-made questionnaires of Managers’ skills containing 22 items and with the reliability coefficient as 0.96, and Professionalism containing 28 items and the reliability coefficient as 0.95. Their validity was investigated and confirmed by professors and experts of management. Analyzing data was conducted at the two level of descriptive statistics (frequency, mean, SD, and presentation of tables and charts) and inferential statistics (one sample t-test, correlation coefficient, regression coefficient, ANOVA, and F-test).

Sign in / Sign up

Export Citation Format

Share Document