Application of AI technology in personalized recommendation system for financial services

FinTech field began to develop rapidly since 2008, after the Global Financial Crisis. This was due to the fact that financial institutions could not quickly respond to consumer needs because of a number of regulatory and legislative restrictions that were implemented to overcome the consequences of the crisis. At the same time the main factors of FinTech development were technological evolution, emerging customer expectations, availability of funding and capital, and support from governments and regulatory authorities. FinTech makes traditional financial services more affordable, flexible and secure, and therefore FinTech is one of the main drivers of digital transformation of the whole financial sector and the development of financial accessibility in the world. The development of the FinTech industry has a huge influence on the financial sector. FinTech strives to make financial services more accessible for both consumers and businesses. FinTech companies are fast growing and attract a large amount of investment each year in their development. At the same time, traditional financial institutions feel threatened on their part, because with the increasing number of FinTech companies, competition in the financial services market is growing too. In order to stay on the market, traditional banks are forced to adapt to modern realities and develop cooperation with FinTech companies. FinTech companies can help banks provide financial products and services more effectively and strengthen their competitive advantages. For example, they can improve financial inclusion, enhance customer experience, increase transparency, improve security, and provide support and guidance. Thus, financial institutions in cooperation with FinTech companies are able to provide new financial products and services to groups of customers who previously did not have access to traditional financial services. In addition, thanks to new technologies, financial institutions can offer personalized services and communicate online with customers, which significantly increases their engagement and experience. Furthermore, FinTech companies can help financial institutions detect fraud and deal with cyber-attacks and other online risks. Keywords: FinTech, financial technologies, financial services, financial innovations, FinTech adoption.

With the increasing aging population, it has had a profound impact on the financial services industry and economy. This study aims to explore the effect of population aging on the financial service industry and economy and propose corresponding countermeasures and suggestions. The aging population has brought challenges to the financial services industry. The increase in the elderly population has led to a rise in demand for financial products and services. Financial institutions innovate and develop financial products and services that meet the needs of older people. At the same time, the financial literacy of older people is relatively low, and financial institutions need to strengthen financial education and improve their financial knowledge level. Secondly, the aging population has had multiple economic impacts, with decreased labor supply and increased elderly care expenses putting pressure on economic growth. Financial institutions must pay attention to this trend, adjust loan policies, and support the development of emerging industries to promote sustainable economic growth. In addition, the change in the consumption needs of older adults has also brought new opportunities to the economy. Financial institutions can meet the consumption needs of older people and promote economic development through innovative products and services.

Purpose: Financial institutions engage in performing imperative part in the economic development of an economy through circulation of funds that resulting in employment and fair distribution of limited resources. Financial literacy results in usage of financial product and services provided by financial institutions that lead to pervasive growth of an economy. Financial inclusion takes into loop the excluded segment of a developing country to attain the desired financial and economic outcomes. Recognizing the importance of financial inclusion, this study is executed to investigate the impact of financial literacy on financial inclusion in street vendors.
 Design/methodology/approach: This study was conducted in twin cities Islamabad and Rawalpindi. Snowball and purposive sampling technique has been used in this study. Primary data has been collected from street vendors through semi structure interviews and questionnaire. Participatory action research design is used in this study. Deductive approach has been used for qualitative data analysis.
 Findings: The results of this study found that street vendors only name financial institutions. They don’t have knowledge about financial products and services provided by those financial institutions. Because of inadequate knowledge, majority of the street vendors do not use financial products and services which are available to them. A very small number of street vendors are using financial products and services. The expected outcomes of this study set a direction for policy makers of financial institutions about how to increase financial inclusion by considering the observed relations in this study.
 Practical implications: The results will help policy makers in formulating effective strategies to bring into the net that excluded segment, which if included will not only improve their quality of life but also augment to the sustainability and growth of economy through financial inclusion.
 Originality/value: As suggested by the recent relevant literature, the study is an attempt to identify those antecedents of financial inclusion, which has not been explored earlier in context of Pakistan, to extend the earlier findings through qualitative research method and to establish how financial inclusion can be made a success in achieving its desired outcomes in a developing economy.

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

Purpose – The purpose of this paper is not only to design a more effective recommendation system for libraries, but also to eliminate many of the weaknesses found in the existing library recommender systems.Design/methodology/approach – A novel library recommender system was designed for English collections by integrating personal ontology model and collaborative filtering model with domain specification.Findings – The trend of the traditional library is evolving toward that of digital library. The personal ontology recommender (PORE) system offers a friendly user interface and provides several personalized services.Research limitations/implications – This system is only implemented and tested in the Library of National Chung Hsing University in Taiwan.Originality/value – The paper demonstrates a good methodology to offer an active, effective, and personalized recommendation system for library patrons.

Application of classification and regression tree (CRT) analysis to identify the agricultural households at risk of financial exclusion

The main goal of this article is to understand the potential learning applications based on AI technologies for health higher education students. We employed a Systematic Literature Review, contributing to explore to what extent AI technologies are currently influencing the Health learning processes in higher education and the skills developed during the learning path. The intent is to contribute to a more profound understanding of learning contexts, methodologies, technologies, and pedagogical processes with the application of AI technologies. The literature emphasizes that AI can be used to potentiate the learning process and the learning outcomes, especially in laboratory classes, and such contexts are still largely unstudied. To fulfil this gap, some practical applications based on AI technologies applied to health higher education studies were identified, highlighting AI's innovations and possible opportunities for health higher education.

Financial services industry has always been a data-intensive industry, generating large quantities of customer data from millions of transactions conducted every day. Vast explosion of data and the surge in technological complexities is transforming the way the financial sector operates, and thus, Big Data management of various financial products and services is emerging as a potential field of study. The application of Big Data in financial services has abundant advantages for the financial institutions: improved customer engagement, better fraud detection, and enhanced market trading analysis. This chapter presents applications of Big Data stimulating various financial sectors and highlights its influence on financial markets, financial institutions, fraud detection, risk analysis, etc. The association between Big Data and finance-related mechanisms is analyzed through an exploratory literature assessment. This chapter also describes real world, contemporary case studies on the applications of Big Data in the financial world. The findings demonstrate that there are many technological research challenges at all levels of Big Data chain that need to be developed to provide more competitive and effective solutions. Since Big Data is a relatively new concept in the field of finance, this study also provides directions for future research.

Islamic banking and finance industry is a speedily and widely-ranging growing sector globally since its structured business initiation in the late 20th century AD. It is actual fact that Islamic and non Islamic nations are seriously concerning their curiosity to implement this potential banking and finance system in their countries and states presently as a result of negative impacts of burdensome interest system on their economics. At the same time, Islamic banking industry started its functions few decades ago among the influence of well established conventional banking and finance sector in Sri Lanka and it is developing gradually among the Muslims and other community people. However, it is notable that in Sri Lanka where Muslims are living minority level, the Islamic banking and financial institutions have to confront a number of challenges in their daily functions and the development as well. Consequently, the main objective of this study is to clarify the major Challenges faced by Islamic financial institutions in Sri Lanka. Accordingly, the study is designed as qualitative method and personal direct interview with semi structured questionnaire is used in data collection. The questionnaire for interview is dealt with selected important matters relating to the particular study. Furthermore, the secondary data required is also collected and utilized from related literatures and sources. Descriptive statistic analytical techniques are used in data analyzing to carry out the study effectively. In this context, the findings reveal that there are many negative impacts faced by Islamic banking and financial institutions in Sri Lanka in the operations of offering Shariah compliant products and services by means of the major challenges. Consequently, it is much important to find proper solutions to overcome these challenges and in the development of the sector. KEY WORDS: Islamic Financial Institutions, Challenges, Shariah compliant, Sri Lanka, Finance Products and Financial Services

Recommender System was widely used in commercial websites for the past few years. These systems track past activities of customers and recommend them the relevant items. The emergence of E-learning activities over a few decades develops a variety of E-learning content available for virtual learning environments (VLE). A large amount of learning objects is present in E-learning repositories. Dealing with problems of the diversity of data, Educational Recommender System (ERS) plays a vital role in the educational sector. Educational recommender systems track the learners' past activities, know the users' preferences, assist the educators and learners, provide relevant content to learners, and enhance their learning outcomes. A personalized recommender system will intensify the learners' interest in particular content and reduce the course dropout rate. The recommender system makes the decision-making process for choosing the appropriate content easy for learners. ERS uses various approaches and technologies for assisting the learners' and helps them to run their learning process smoothly. Collaborative filtering, Content-based, and knowledge-based are the basic techniques of recommender systems. The research shows that a combination of these approaches will give more effective and efficient results. This mixing of approaches refers to the hybridization techniques. Traditional approaches with deep learning networks will improve the recommendations and provide results with higher accuracy. This paper provides how E-learning support recommender systems produce recommendations using different techniques. The technical results of recommender techniques help to find the best approach for making a recommender system in the future.

AI public sports teaching technology is applied to daily indoor or outdoor fixed sports tests, ability assessments, and sports classroom teaching scenarios. It provides automated voice broadcast guidance, sports video AI intelligent engine automatic analysis, real-time detection of illegal actions, and intelligent real-time output of sports test results; Through AI intelligent guidance, the whole process of basketball test sports analysis and training suggestions are realized, and students are encouraged to conduct self-evaluation, promote training through testing, and practice more frequently. It also promotes the normalization of sports testing/teaching in public physical education in colleges and universities through teaching demonstration video explanations and a combination of various classroom forms, accumulates campus physical test data, and assists public physical education teaching and testing in colleges and universities. AI technology has intelligent joint detection and marking, multi-subject tracking and recognition. It does not require any markers to be installed on the captured object, and can capture accurate motion through video. During the basketball test, if an abnormal situation occurs, the student needs to stop the test. AI technology uses motion capture and analysis systems to help students and teachers better understand the sports skills and techniques tested in basketball, thereby developing more effective sports teaching and training plans. Motion capture and analysis systems can be used to evaluate athletes’ gait and posture to help them improve their techniques and reduce the risk of injury.

With the rapid development of artificial intelligence, AI technology has been widely applied in various industries, including education. In English teaching, AI technology provides teachers with objective and instructive feedback, offers students a more personalized learning experience, helping them improve their English language skills, etc., and brings new development opportunities and challenges to English teaching as well. However, there are still some problems that need to be solved in college English teaching in our university. For this reason, based on the application of AI technology in college English teaching, this paper mainly explores the impact and application countermeasures of AI on college English teaching from the following four aspects: individuals with differences, teaching management, classroom teaching and teaching evaluation. In addition, the profound integration of college English education and AI will foster the advancement and transformation of college English instruction, ultimately serving as a catalyst for its reform.

Recommendation technology is an essential component of the Internet of Things (IoT) services that can help users get information at any time and from any place. Traditional recommendation algorithms, on the other hand, are unable to satisfy the IoT environment’s swift and reliable recommendation criteria. The use of mathematical and information discovery methods to overcome the relationship with target consumers in order to have desired items is known as a recommendation system. In this paper, a recommendation algorithm based on collaborative filtering is proposed. In this sense, the recommendation method (Recommender Systems) was developed; it is focused on the user’s characteristics, such as hobbies, and it is recommended to satisfy the object’s user specifications, also known as customized recommendation system (Personalized Recommender Systems), The majority of modern e-commerce recommender programs tend to recommend the best goods to a customer, believing that each product’s properties remain constant. Some properties, such as price discounts, can, however, be customized to respond to the preferences of each customer..

This research is motivated by the important role and features of Micro, Small and Medium Enterprises (MSMEs) in surviving the economic crisis and the high contribution to Gross Domestic Product (GDP) as well as when compared to large businesses. Even though it has a big role, MSMEs still have some problems, one of which is limitations on financial literacy. Limited literacy is a challenge in itself, considering that financial literacy can increase the ability to manage finances and access available financial products. In addition, this study also includes the used of digital finance variables because the 4.0 revolution has entered into everything that is digital-based. In addition, using these variables is also due to the emergence of optimism about the adopted telephone and internet. The used of digital finance in this study focuses more on payments produced by financial institutions and financial technology companies.The effects of these two variables on financial inclusion will then be examined considering their role in reducing the limited access to available financial services and thus encouraging economic growth. The city of Bandung is used as a research area. Bandung City was choosen because the large number of MSMEs and Bandung City MSMEs have their own characteristics. Based on the Dinas Koperasi dan UMKM Kota Bandung (2018), there are 5.242 micro businesses in Bandung City, 23 medium scale businesses, and 394 small-scale businesses so that the total number is 5.841 MSMEs. The research method used is explanative to explain the relationship between variables through purposive sampling so that 56 respondents were obtained. The purposive sampling technique using the following considerations: categorized micro, small and medium enterprises, business activities in Bandung city, and willing to provide the necessary information. In variable measurement, financial literacy is measured by knowledge related to finance and financial services, actions in making financial decisions, the ability to manage finances, tell financial concepts, and attitude in responding to financial related matters based on Bongomin, Munene, Ntayi, and Malinga (2017), Bongomin et al. (2016), Nkundabanyanga, Kasozi, Nalukenge, and Tauringana (2014), Kartawinata and Mubaraq (2018), and Sina (2017). Measurement the used of digital financial variable adapted based on Azam (2015), Zhou, Lu, and Wang (2010), and Qian, (2019) which consisted of perceptions of ease, benefits received, perceptions of used transfer activities, payments, and account management. Likewise financial inclusion, the measurement of which was adapted from Bongomin et al. (2017) and Bongomin et al. (2016) which consists of the ability to access financial services, using financial services, the quality of financial services, and the benefits obtained when using financial services.The data in this study are primary data with a questionnaire for further analysis using Partial Least Square (PLS). The Likert scale used in this study consists of 4 scales. The answer options strongly disagree are given value 1, disagree is given value 2, agree is given value 3, and strongly agree is given value 4 (Hermawan & Yusran, 2017; Martono, 2016). These four scales to reduce a neutral choice answers that do not show partiality towards positive or negative which results in a tendency not argue. PLS is used as a causality testing analysis tool due to the similarity of objectives with the research conducted and its used which can manage small amounts of samples. The minimum sample size in PLS is 10 samples on each line jalur (Abdillah & Hartono, 2015). In testing the hypothesis, a confidence level of 90 percent is used. Validity testing uses loading scores, AVE values, comparing indicator’s loading and cross loading, and comparison AVE roots with correlation. In this study also use reliability testing with composite reliability and KR-21 considering that the measurements carried out in the study were one measurement.The results show both variables have a positive influence and a very strong level of significance on financial inclusion. This result also supported by very strong evidence that can be seen through the p-value for each relationship. The results of the research prove that barriers to accessing these services can be minimized through increasing financial literacy so that can increase financial inclusion and be more developed. Therefore, a common problem experienced by MSME actors, namely low financial literacy, is a serious problem that can be overcome with training or coaching as consideration for solutions considering that financial literacy can open financial access to be more developed. Touching MSMEs with the used of digital finance will automatically open their ability to access available payment financial services and increasing financial inclusion.

Nowadays, large volumes of valuable data of different degrees of veracity can be easily generated or collected at a high velocity from a wide variety of data sources. Embedded in these big data are implicit, previously unknown and potentially useful information and knowledge. Hence, big data analytics are in demand as they assist users to analyze the big data and discover new knowledge. This in turn helps users gain insight into big data, obtain useful information, and make personalized recommendation. In this paper, we focus on big data analytics on music-i.e., music analysis-for personalized music recommendation systems. In particular, we present a system that exploits the frequent tags attached to the tracks in an user's listening history and a hidden Markov model (HMM) for generating predictions and thus making personalized recommendation. Knowledge learned from this personalized music recommendation can be transferred to building other personalized recommendation systems.