1 |
Classification Method of Financial Behaviour Through Means of Machine Learning : Can a classification method created using bank transaction and machine learning help individuals to understand their spending behavior?Cheng, Yilei, Al-Sayed, Akhmed January 2022 (has links)
With the current fast transformation from physical cash to digitized banking systems, there are more and more people that are at risk of overspending without realizing it. There are methods and researches done that are targeted at incorporating machine learning in identifying fraudulent transactions and credit scores but currently there is no research done in categorizing people’s behaviour based on transaction records using machine learning techniques. The purpose of this project is to create such classification method based on income and spending. We propose a classification model based on k-means clustering and neural network techniques that categorizes people’s spendings behaviour based on monthly transaction records. The goal of this work is to contribute to one’s understanding of personal spending behaviour. The research question posed to achieve this is: can a classification method created using bank transaction and machine learning help individuals to understand their spending behaviour? This work is intended to be a basis for future research in studies in spending behaviour classification. The result shows the final method consists of a pipeline of simplifying bank transaction dataset, k-means, data augmentation and artificial neural network. It is capable of classifying spending behaviours based on characteristics such as ”low income and high spending” or ”high income and low spending”. The general approach for research method of this thesis is qualitative and inductive / Med samtida förändringar från fysiska pengar till digitala banksystem så riskerar människor att spendera för mycket utan deras vetskap. Det finns metoder och forskning som inriktar sig mot att inkorporera maskininlärning bland identifieringen av bedrägliga transaktioner och kreditpoäng, men för närvarande finns det ingen forskning inom kategoriseringen av människors beteende, baserat på transaktionsuppgifter som använder sig av tekniker inom maskininlärning. Syftet med denna avhandling är att skapa ett sådant klassifikationssystem baserat på inkomst och utgifter. Vi föreslår en klassifikationsmodell som baseras på ‘K-means’ gruppering och artificiella neuronnät-tekniker som kategoriserar människors spenderande genom att undersöka uppgifter om personliga utgifter. Målet med arbetet är att bidra till förståelsen av konsumtionsbeteende. Därför är avhandlingens frågeställning: kan en klassifikationsmetod som använder sig av banktransaktioner och maskininlärning hjälpa människor att förstå sitt beteende kring spenderande? Detta arbete är menat att vara till grund för framtida forskning inom konsumtionsbeteende. Resultaten visar på att den slutgiltiga metoden består av ett flöde för att förenkla dataset om banktransaktioner, “K-means”, datasökning, och artificiella neuronnät. Metoden är kapabel av att klassificera beteenden baserat på karaktärsdrag såsom ”låg inkomst, hög nivå av spenderande” eller ”hög inkomst, låg nivå av spenderande”. Avhandlingens ståndpunkt är kvalitativ och induktiv
|
2 |
A spending behaviour model for selected South African arts festivals / Veronique LabuschagneLabuschagne, Veronique January 2014 (has links)
Arts festivals form a large part of the South African culture originally as many local communities began to share their culture with visitors by means of arts festivals. This has grown into a large industry that has tremendous financial gain for the hosting communities. With over 500 arts festivals each year in South Africa alone, visitors are certain to find a festival to satisfy their specific needs and wants. Therefore, with so many genres available, each festival has created its own niche market and loyal customer base.
An extensive literature study was conducted for the purpose of this thesis and it was found that research of small to medium arts festivals has been neglected. This finding motivated the main theme of this research. As mentioned earlier, there are so many genres available that the festival organisers may experience difficulty when deciding what to offer and how many genres to offer in order to still be sustainable and attract a sufficient number of visitors. Furthermore, the large number of arts festivals organised each year makes it increasingly difficult for festivals to build a loyal client base. First-time visitors can be converted into repeat visitors if the marketing strategy is precise. Repeat visitors, as stated in the literature, results in a sustainable income for each festival.
Another question that motivated the research was the location of the three arts festivals (Innibos, Vryfees, and Kierieklapper). Three arts festivals in three provinces makes an interesting study to determine whether there is a difference in the three types of visitors that they attract and the spending patterns at each festival.
While addressing the problems stated above, this study produced the following three articles:
* Article 1: ―Determinants of spending at Vryfees with a focus on genres‖.
* Article 2: ―First-time versus repeat visitors at Innibos Arts Festival‖.
* Article 3: ―Role of location in the attendance and spending of festinos‖.
Article 1 investigates spending determinants that influence visitor expenditure on the different genres offered at the Vryfees Festival in Bloemfontein, based on a survey conducted in 2011. The research is based on the notion that different genres have different spending patterns. Article 2 focuses on the differences and/or similarities between first-time and repeat visitors at the Innibos Arts Festival as an alternative approach to market segmentation. Lastly, the third article focuses on three different arts festivals in three different locations in South Africa. The research was conducted by means of a visitor survey at the three arts festivals during the same year with questionnaires administered at Innibos (428), Vryfees (336), and Kierieklapper (202) respectively.
The most significant contributions of this study can be summarised as follows:
* the tourist spending behaviour in regards to the difference between first-time and repeat visitors is significant and can be considered an important spending determinant;
* the tourist spending behaviour in terms of length of stay between first-time visitors and repeat visitors is significantly different, suggesting that familiarity with the destination (as the repeat visitors are) has an important impact;
* different locations attract their own type of tourists and certain locations receive a higher economic injection than other provinces do because of the type of festival held. All three arts festivals attract mainly Afrikaans speaking attendees; and for the first time, a comparative study has been conducted on three arts festivals targeting the Afrikaans speaking community. Additionally, this is the first time a comparative study was conducted on three small to medium arts festivals located in three different provinces; and
* the developed spending model described in the last chapter of this thesis can assist the festival organisers with future festival marketing to improve their income and marketing strategy. / PhD (Tourism Management), North-West University, Potchefstroom Campus, 2014
|
3 |
A spending behaviour model for selected South African arts festivals / Veronique LabuschagneLabuschagne, Veronique January 2014 (has links)
Arts festivals form a large part of the South African culture originally as many local communities began to share their culture with visitors by means of arts festivals. This has grown into a large industry that has tremendous financial gain for the hosting communities. With over 500 arts festivals each year in South Africa alone, visitors are certain to find a festival to satisfy their specific needs and wants. Therefore, with so many genres available, each festival has created its own niche market and loyal customer base.
An extensive literature study was conducted for the purpose of this thesis and it was found that research of small to medium arts festivals has been neglected. This finding motivated the main theme of this research. As mentioned earlier, there are so many genres available that the festival organisers may experience difficulty when deciding what to offer and how many genres to offer in order to still be sustainable and attract a sufficient number of visitors. Furthermore, the large number of arts festivals organised each year makes it increasingly difficult for festivals to build a loyal client base. First-time visitors can be converted into repeat visitors if the marketing strategy is precise. Repeat visitors, as stated in the literature, results in a sustainable income for each festival.
Another question that motivated the research was the location of the three arts festivals (Innibos, Vryfees, and Kierieklapper). Three arts festivals in three provinces makes an interesting study to determine whether there is a difference in the three types of visitors that they attract and the spending patterns at each festival.
While addressing the problems stated above, this study produced the following three articles:
* Article 1: ―Determinants of spending at Vryfees with a focus on genres‖.
* Article 2: ―First-time versus repeat visitors at Innibos Arts Festival‖.
* Article 3: ―Role of location in the attendance and spending of festinos‖.
Article 1 investigates spending determinants that influence visitor expenditure on the different genres offered at the Vryfees Festival in Bloemfontein, based on a survey conducted in 2011. The research is based on the notion that different genres have different spending patterns. Article 2 focuses on the differences and/or similarities between first-time and repeat visitors at the Innibos Arts Festival as an alternative approach to market segmentation. Lastly, the third article focuses on three different arts festivals in three different locations in South Africa. The research was conducted by means of a visitor survey at the three arts festivals during the same year with questionnaires administered at Innibos (428), Vryfees (336), and Kierieklapper (202) respectively.
The most significant contributions of this study can be summarised as follows:
* the tourist spending behaviour in regards to the difference between first-time and repeat visitors is significant and can be considered an important spending determinant;
* the tourist spending behaviour in terms of length of stay between first-time visitors and repeat visitors is significantly different, suggesting that familiarity with the destination (as the repeat visitors are) has an important impact;
* different locations attract their own type of tourists and certain locations receive a higher economic injection than other provinces do because of the type of festival held. All three arts festivals attract mainly Afrikaans speaking attendees; and for the first time, a comparative study has been conducted on three arts festivals targeting the Afrikaans speaking community. Additionally, this is the first time a comparative study was conducted on three small to medium arts festivals located in three different provinces; and
* the developed spending model described in the last chapter of this thesis can assist the festival organisers with future festival marketing to improve their income and marketing strategy. / PhD (Tourism Management), North-West University, Potchefstroom Campus, 2014
|
Page generated in 0.0635 seconds