Applying the CRISP-DM data mining process in the financial services industry: Elicitation of adaptation requirements

Plotnikova, Veronika; Dumas, Marlon; Milani, Fredrik

doi:10.1016/j.datak.2022.102013

Cited by 26 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Then there is research from Veronika Plotnikova et al (2022) conducted research by trying to apply CRISP-DM to the financial services industry as one of the methods for carrying out the data mining process. The research results identify the consistency in the CRISP-DM lifecycle, impacts, and solutions to overcome gaps if used the CRISP-DM model in the financial service industry [10].…”

Section: Approach To Data Explorationmentioning

confidence: 94%

Product Clustering in the Msme Business of Grocery Store

Saptadi¹,

Arvianto²,

Dhima³

et al. 2022

IJASER

View full text Add to dashboard Cite

The business world is an exciting world to follow due to its dynamic and competitiveness. Sri Wahyuni Grocery is one of the MSMEs involved in buying and selling daily-basis needs. The business can manage an average of 115 transactions in a day, including various transactions for necessities. Most products purchased at this grocery shop are daily basic needs, such as sugar, tea, instant food, snacks, and fuel oil. It is known that from observations, some products are less desirable by buyers so they are not selling well and some products are selling well, so it is necessary to do a product grouping process to find out how to group these products. An analysis of existing data is needed to obtain information with the K-Means Clustering algorithm. This research aims to determine the pattern of transaction data owned by Traditional Grocery Store MSMEs and form a Clustering pattern of products offered by Traditional Grocery Store MSMEs. Through the data exploration process, this research will carry out a pattern search from transaction data and clustering patterns owned by Traditional Grocery Store MSMEs. Based on the findings from the research conducted, business actors will be able to develop various strategies to improve services to sales by relying on the use of various data mining algorithms. The research was conducted on Traditional Grocery Store MSMEs with transaction data for two months, and the research carried out data exploration to determine clustering patterns using the CRISP-DM method.

show abstract

Section: Approach To Data Explorationmentioning

confidence: 94%

Product Clustering in the Msme Business of Grocery Store

Saptadi¹,

Arvianto²,

Dhima³

et al. 2022

IJASER

View full text Add to dashboard Cite

show abstract

“…Some of the advantages of CRISP-DM are highly efficient [17] and make the result of data mining available more accurately and quickly [18]. It is often adapted to accommodate domain-specific requirements [19]. It has six phases which are business understanding, data understanding, data preparation, modelling, evaluation and deployment [17], [18], [20].…”

Section: Methodsmentioning

confidence: 99%

The prediction of student’s academic performance using RapidMiner

Firdaus Mustapha,

Izzah Zulkifli,

Kairan

et al. 2023

IJEECS

View full text Add to dashboard Cite

Students’ performance analysis basically consists of determining the factors influencing the performance and how it will give impact towards success. It will help us to understand students’ behavior and how to improve their academic performance. The efficiency of this analysis depends on the information given by the user through learning management system (LMS). In order to improve the information, we have applied algorithms on the dataset and prepared a model by using Tableau and RapidMiner. Cross-validation with decision tree also has been applied on datasets. This can help in evaluating statistical computational results into a generalized data set. Based on the calculation of data mining, it can analyze that our model is quite stable since it has high accuracy with lower standard deviation. So, the processes like testing and validation, applying the model and decision tree on RapidMiner generates the output in a specific form. The result shows that the percentage of students who are absence is better than students who are absence more than 7 days. At last, a model is prepared, and it can help the schools, students, and the parents in adapting appropriate measures to ensure the success of students at school.

show abstract

“…This phase entails a meticulous exploration of the multifaceted dimensions surrounding waste management dynamics, encompassing factors such as demographic trends, socio-economic indicators, tourism influxes, and industrial activities. Through a nuanced understanding of these contextual nuances, the research seeks to delineate a comprehensive framework that encapsulates the intricate interplay between various drivers influencing waste generation patterns [14]. Furthermore, this stage necessitates active engagement with stakeholders, including local authorities, waste management agencies, environmental experts, and community representatives.…”

Section: Business Understandingmentioning

confidence: 99%

“…Once the business understanding stage is completed, the subsequent step, as illustrated in Figure 1, delves into a multifaceted process encompassing the identification and comprehensive understanding of the data at hand, data collection or acquisition, meticulous data analysis, and rigorous validation of the prevailing data quality [14]. This pivotal stage serves as the bedrock for the ensuing analytical endeavors, aiming to foster a profound comprehension of the dataset earmarked for analysis.…”

Section: Data Understandingmentioning

confidence: 99%

Prediction of Waste Generation in Yogyakarta Special Region Province Using ARIMA Model

Azizah

2024

IJIIS Int. J. Informatics Inf. Syst.

View full text Add to dashboard Cite

Waste management poses a significant challenge in densely populated urban areas of Indonesia, particularly in the Special Region of Yogyakarta, which grapples with both a large populace and robust tourism industry. The region witnesses a staggering 11.53% annual uptick in waste accumulation, exacerbating the strain on existing waste management infrastructure. Addressing this pressing issue necessitates a comprehensive analysis to forecast waste generation trends, enabling the formulation of effective management strategies. This study employs the CRISP-DM framework, facilitating a structured approach to analysis and informed decisionmaking. Utilizing a time series dataset spanning from 2016 to 2022, detailing waste generation across various districts and cities, the research employs the ARIMA model for predictive analysis. This model, renowned for its suitability in time series forecasting, emerges as the preferred choice. Projections derived from the ARIMA model reveal a notable surge in waste generation across the Special Region of Yogyakarta from 2023 to 2025. Specifically, it is anticipated that the aggregate waste output will escalate from 638 thousand tons in 2022 to 642 thousand tons in 2023, with an anticipated annual increase ranging between 5 to 7 thousand tons thereafter. These forecasts underscore the urgency of implementing proactive measures to mitigate the burgeoning waste management challenges facing the province.

show abstract

Applying the CRISP-DM data mining process in the financial services industry: Elicitation of adaptation requirements

Cited by 26 publications

References 10 publications

Product Clustering in the Msme Business of Grocery Store

Product Clustering in the Msme Business of Grocery Store

The prediction of student’s academic performance using RapidMiner

Prediction of Waste Generation in Yogyakarta Special Region Province Using ARIMA Model

Contact Info

Product

Resources

About