Next Article in Journal
Exploring the Use of Crypto-Assets for Payments
Previous Article in Journal
Banking Transformation Through FinTech and the Integration of Artificial Intelligence in Payments
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
FinTech
Volume 4
Issue 2
10.3390/fintech4020014
fintech-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Automated Ledger or Fintech Analytics Platform?

by
Andrew Kumiega
Stuart School of Business, Illinois Institute of Technology, Chicago, IL 60616, USA
FinTech 2025, 4(2), 14; https://doi.org/10.3390/fintech4020014
Submission received: 10 December 2024 / Revised: 19 February 2025 / Accepted: 24 February 2025 / Published: 2 April 2025
Browse Figure
Versions Notes

Abstract

:
Initially designed as an automated ledger tool, Excel swiftly evolved into a data analytics platform for financial analysts to execute intricate financial analyses. Excel is so commonplace in the financial industry that many do not even consider it a fintech tool. The transformation of Excel from a simple ledger tool to a low-code machine learning (mL) platform is not a traditional focus for fintech. The transformation of Excel into an mL platform will let financial analysts and quantitative analyses quickly evolve financial models in Excel to use advanced mL techniques. The low-code interface lets analysts quickly build predictive models. This paper explores how Excel has evolved into a low-code machine platform for financial applications along with the risks associated with Excel’s new functionality.

1. Introduction

Fintech, the integration of finance and technology, has rapidly redefined how financial professionals use data. A critical tool in this evolution has been Microsoft Excel, which started as a ledger automation tool and has grown into a powerful platform for financial analytics, modeling, and decision support. Excel’s continuous transformation into an analytics integrated development environment (IDE), which enables users to enhance existing Excel-based solutions with innovative predictive analytics problems without writing code, is the key question, not whether it is a finance technology platform.
Microsoft Excel is a widely used tool in finance, valued for its simple ribbon-based interface that allows end users the ability to organize data, and create complex financial calculations, visual analytics, and statistical analyses for a multitude of financial problems [1,2,3,4]. Despite the advent of specialized financial software, Excel remains a popular choice among financial professionals. Its extensibility through third-party user-friendly interfaces and seamless integration with other financial applications are key factors in its popularity. The demand for sophisticated Excel-based models and modelers remains strong. An illustration of this can be seen in the recent development of the Chartered Financial Modeler and Master Financial Modeler certifications, which were created to complement the CFA. In fact, a board member was the president and global CEO of the CFA Institute, which shows Excel skills are still important in finance [5].
Some organizations are recognizing the limitations of Excel, including capacity constraints, scalability issues, and computational limitations, as financial data become increasingly complex. This has led to the adoption of more specialized programming languages such as Python, JavaScript, and Haskel [6]. These tools offer greater computational power and data handling capabilities. Excel, however, continues to evolve beyond being a traditional spreadsheet tool to become a hybrid financial platform. With built-in support for Python, SQL, OLAP, and advanced solver capabilities, it now offers enhanced analytical capabilities within its familiar interface [7].
Rather than debating Excel vs. Python, we should focus on how Excel has become an integrated platform, bridging the gap between traditional financial tools and modern programming languages [8]. The ability to bridge this gap is because the interface that most users think of as Microsoft Excel is actually a graphical user interface (GUI) on top of a C++ software program that is specifically designed to perform mathematical calculations. The finance community has been using this structure to program Excel in C++ to make desktop trading applications since the mid-1990s [9]. The ability to control these third-party tools through the ribbon interfaces further enhances the functionality of Excel.
Excel’s architecture, through the Office Component Object Model (COM) framework, as partially shown in Figure 1, supports integrating third-party math tools and even other C++-based programming languages.
By incorporating data and mL tools into Excel using the COM framework, particularly with the addition of Power Query, Power BI, Python, SAS, @Risk, Python, and Advanced Solver, a low-code platform for complex predictive analytics for financial data has been created. This low-code platform will let financial analysts quickly integrate mL tools into traditional financial analysis models. This low-code platform eliminates the need for programming assistance from IT and empowers analysts to perform complex analysis on their own.
Here are some examples of how to use Excel as a low-code analytic IDE:
1.
Credit risk modeling: One of the most critical tasks for analysts is assessing credit risk for individual clients or portfolios of loans. Many credit modeling books with Excel examples document the long-standing use of Excel for credit analysis in finance. Using Excel’s embedded Python libraries, Advanced Solver add-ins, or Neurosolution add-ins, analysts can quickly apply mL models such as logistic regression, decision trees, and random forests to predict default probability [10,11].
○
Task example: Use Excel’s Power Query to gather loan data, clean it with data transformation tools, and then use various mL algorithms via Python code, Advanced Solver, or SAS to create an ensemble that predicts loan default likelihood. Excel provides a direct visualization of the results for decision-making [12,13].
2.
ML tools can enhance portfolio optimization by identifying patterns and anomalies in market data that traditional financial models might overlook. For example, CFAs can use clustering algorithms like K-Means to segment assets based on performance and risk features, which can help refine investment strategies [14].
○
Task example: Download a portfolio into an Excel Sheet. Then, use Excel’s Python integration to apply clustering algorithms to classify assets. Then, apply mL models to predict returns based on historical patterns, making sure high-risk assets are balanced with more stable investments [15,16].
3.
Predictive market analysis: CFAs can use Excel’s mL capabilities to build models that predict market movements based on historical data and external financial indicators [17]. Financial analysts can use Python libraries to implement techniques like time series analysis (ARIMA, GARCH models), which let them forecast stock prices, commodity trends, or foreign exchange movements [18,19].
○
Task example: Use Excel’s Power Query and Python integration to import historical stock market data, clean it, and then apply a time series model like ARIMA to forecast future stock prices. Excel’s visualization tools can then connect this model to create real-time dashboards for tracking stock performance and making investment recommendations [20].
Introducing database tools, predictive modeling, optimization algorithms, and Python into the Excel low-code framework significantly alters Excel’s functionality, particularly in terms of analytics. Financial analysts can now construct applications that were previously exclusive to programmers. They can enhance spreadsheets with advanced stats without rewriting them in Python, R, or JavaScript. A low-code setup makes it quick and easy for anyone to create powerful Excel-based tools.

2. Excel Has Evolved into a Low-Code IDE, but What Programming Paradigm Does Excel Use?

There are three programming paradigms: procedural, object-oriented, and functional. Procedural languages, like C and Pascal, are sequential languages that are step-by-step-based [21]. Object-oriented languages, such as C++ and Java, create objects that encapsulate logic and data [22]. Functional programming treats computation as evaluating mathematical functions, emphasizing immutability.
Excel’s development environment supports all three paradigms. Excel’s IDE allows the mixture of all these paradigms in a single application. Two major tools, VBA (Visual Basic for Applications) and the recently added support for Python, expand Excel’s programming capabilities beyond the functional paradigm that dominates most of its usage. These tools significantly enhance automation and customization, which are invaluable for financial analysts working in fintech.
VBA has long been a staple in Excel, letting financial professionals create macros that automate repetitive tasks, such as generating financial reports, running simulations, or processing large datasets [2,23]. VBA operates within a procedural paradigm, where analysts write step-by-step instructions to manipulate data and objects like ranges, cells, and charts [9].
Python increases Excel’s ability to perform complex statistical analysis of data. Python, a versatile and widely used language in the fintech space, is renowned for its advanced data manipulation libraries like Pandas and NumPy and its mL capabilities [24]. By integrating Python directly into Excel, financial analysts can now access many statistical libraries, such as Pandas and NumPy, to perform predictive modeling and automate intricate financial processes that would have been cumbersome or impossible with VBA alone.

3. Excel Evolution into an IDE

Excel’s transformation over the last three decades from a simple ledger to a development environment for high-level analytics, including mL, has been gradual. Many users who still use Excel to build traditional applications have largely overlooked the extent of this shift.
Still, Microsoft has embedded new development platforms into Excel, as described in Table 1. Each addition introduces more software risks, requiring the adoption of new development methodologies and testing techniques. Including multiple mL tools in a spreadsheet allows for the creation of complex mL applications.
Adding all these programming tools to Excel has turned it into an IDE for self-service analytics professionals. All these tools are easily accessible on the toolbar. The toolbar interfaces act as a low-code IDE for these analytic tools. For example, the Power Query toolbar serves as the SQL Server’s graphical query designer, while Power Pivot works as a graphical designer for OLAP. Excel has incorporated low-code tools such as Advanced Solver (XLMiner), XLStat Premium, and SAS through toolbar ribbon integration. These low-code interfaces empower users to quickly analyze financial data without advanced programming skills. Yet this shift from a simple ledger to an IDE for financial analytics has also expanded Excel’s software development risks.

4. Data Management: Opportunities and Risks

4.1. Opportunities

Financial professionals spend a lot of time collecting and organizing data [25]. Recent updates to Excel have introduced low-code tools that let users import, manipulate, and analyze large datasets directly from databases, text files, web pages, and other Excel workbooks within the program (see Table 1).
Power Query provides an intuitive environment for cleansing, transforming, and organizing data before integrating it into Excel. During data shaping, Power Query generates an M-code that analysts can edit for advanced data manipulation. This process lets financial analysts take control of data preparation, reducing their reliance on central IT teams and freeing them to focus on broader data tasks.

4.2. Risk Management

Financial analysts often lack the technical knowledge necessary to manage a production-grade data warehouse in a compliant and secure manner. So, financial firms must address significant compliance risks, particularly those tied to fintech regulations, before letting analysts use tools such as Power Query and the M language in Excel for developing data warehouses.
Building a data warehouse in Excel introduces compliance challenges like those found in SQL Server environments [26]. Poorly optimized queries can overload system resources, leading to potential computer crashes. Also, combining data into a single file through Excel or Python in a low-code environment can create compliance vulnerabilities. Errors by untrained users, such as inadvertently changing or deleting critical data during import or consolidation, may result in noncompliance with data integrity and accuracy standards [27].
To ensure compliance, financial institutions must implement strong controls. Financial institutions must implement strong controls when analysts use tools like Power Query in Excel. These controls must focus on data accuracy and prevent unauthorized changes. They must also ensure compliance with industry standards and regulatory requirements.
At a minimum, the controls listed below should be applied to Excel data warehouses for advanced analytics.
  • Documentation: It is important to maintain comprehensive documentation of all relevant processes and procedures. Regulatory frameworks, such as Section 404 of the Sarbanes–Oxley Act (SOX) and Article 30 of the General Data Protection Regulation (GDPR), require comprehensive documentation of data processes. This includes the use of automated tools such as Power Query in Excel. Scripts generated by Power Query must undergo rigorous code reviews and testing. This is to make sure they meet the above standards. Article 30 of the GDPR requires organizations to keep detailed records of their data processing. It emphasizes the need for transparency and accountability in data management. You need to manage Excel spreadsheets using tools like Power Query or Python with the same level of accuracy as other data storage technologies.
  • Data source mapping: The organization must map each data warehouse to its original source. This mapping ensures a clear data lineage. It meets the data traceability requirements of GDPR and other regulations. Tracing the sources of personal data can improve data practices. It makes them more transparent and correct.
  • Testing: If the original database structure changes, we need to retest the Power Query steps. This is to make sure the data are correct. Before we use these Excel data warehouses for new analytics, we need to retest the integrity of the data. This process aligns with GDPR in terms of data accuracy and minimization. It also aligns with the Sarbanes–Oxley Act (SOX) for accurate financial reporting.
  • Annual audits: A yearly audit of fintech that stores data, including all spreadsheets, is a requirement for both GDPR and SOX. These audits confirm that the data in the spreadsheet match the original data.
  • Implementing these controls enables financial firms to mitigate the risks associated with the use of Excel as a data warehousing tool, while also ensuring compliance with the requisite standards of data governance and regulatory compliance.

5. Data Shaping: Opportunities and Risks

5.1. Opportunities

Data shaping encompasses tasks like cleaning, filtering, aggregating, and transforming datasets to uncover meaningful insights. The recently added data shaping tools in Excel, such as Power Query and Power Pivot, let analysts shape data for both descriptive and predictive analyses.
With Power Query, analysts can streamline processes such as removing duplicates, filtering rows based on specific criteria, splitting columns, and generating custom data using formulas. Power Pivot enables the efficient transformation of raw data into summary tables within a data warehouse. These summary tables form the foundation for creating charts and pivot charts that management relies on to identify trends, patterns, and anomalies. They are also regularly plugged into analytical algorithms like regression models and gradient-boosted trees to provide predictive insights.
While these tools significantly enhance productivity, there are inherent risks when analysts shape data without adhering to best practices. Analysts may lack a full understanding of the problem or dataset, leading to improper filtering, transformation, or cleansing [28]. Users are also vulnerable to formula errors, including syntax and logic mistakes [29]. Integrating these advanced functionalities into Excel shifts data risks from traditional cell-to-cell dependencies to those typically associated with SQL databases.

5.2. Risks

Excel-based data warehouses often function outside formal enterprise data governance frameworks, creating a form of shadow IT. Analysts often share and reuse these repositories to develop new analytical solutions, but this practice introduces significant risks, including data inconsistencies, lack of security controls, and reduced transparency in organizational data management [30]. This informal sharing and reuse of data increases the potential for unauthorized data proliferation, data quality issues, and compliance risks due to misalignment with established data management controls [31].
Broader guidelines that align with ISACA’s Data Management and Governance Framework (PEARCE, 2024) are necessary to address these risks. The spreadsheet should incorporate structured governance for all data sources. Implementing specific data governance controls during the data shaping phase is important. ISACA’s COBIT® Framework [32] emphasizes defining and tracking data ownership, validation protocols, and access controls to ensure data integrity and reliability throughout the analytics life cycle. Establishing these controls will help mitigate risks associated with unmonitored Excel-based data warehouses, aligning with ISACA’s principles of data governance and ensuring reliable, audit-ready analytics.
At a minimum, these controls should focus upon the following:
1.
Data transformation consistency:
In analytics, data transformations are important for preparing datasets. Excel’s IDE enables trouble-free application of transformations like the mean, median, percentile, and z-score without coding, available in Excel, Power Pivot, and Power Query. Python integration further simplifies creating custom algorithms for tasks like outlier removal.
Since each transformation affects predictive algorithms differently, it is important to document the reasoning for each transformation and its impact on the algorithm’s accuracy [33].
2.
Auditing of data shaping:
The review and documentation of the data shaping step should follow traditional risk auditing criteria, which occurs once a year or if there is any change in the underlying data structure.
3.
Management of outliers:
The process for managing outliers must be documented since an outlier can significantly change traditional transformations such as a mean or a standard deviation. To assess the algorithm’s sensitivity to Black Swan risks and ensure robustness and reliability, it is ideal to conduct analytics both with and without outliers [34]. Finally, every time a new type of outlier is identified, the data query will need to be changed and retested.

6. Business Analytics and Intelligence

6.1. Opportunities

The recent expansion of Excel’s IDE to include advanced analytical tools—such as Power Maps, Power BI, SAS, and Advanced Solver (XLMiner)—has opened significant avenues for business analytics and intelligence. These tools help with low-code development environments, letting users construct sophisticated dashboards and predictive algorithms within Excel’s familiar interface [35]. These tools let analysts build complex business analysis dashboards and develop predictive algorithms directly in Excel. As a cloud-based version of Excel, Excel for the web enables the efficient distribution of these dashboards and enhances collaboration through real-time data capture and seamless integration with OneDrive [36].
Combining these tools into a single low-code IDE structure turns Excel into a powerful tool for analytics, but it also exposes organizations to IT risk. A new key risk for these tool sets is model risk. AutoML functions in these tools let analysts build complicated models without understanding the underlying logic or mathematical details. This raises the risk of results that are hard to understand [37]. In high-stakes environments such as finance, this opacity poses potential dangers, as model inaccuracies or biases could lead to suboptimal or harmful decisions.

6.2. Risks

To mitigate these risks, integrating Explainable Artificial Intelligence (XAI) into the model development process is essential. This will ensure the transparency and interpretability of the created analytical models [30]. The measures below are essential for addressing the challenges of model interpretability and mitigating model risk in business analytics applications:
1.
Model comparison and selection:
Develop multiple models, including regressions, decision trees, linear models, and rule-based systems. Analysts should compare and rank these models to comprehend the rationale behind the selection of a specific model [37]. In addition, when model rankings are close, focus on the choice of the simplest model to improve interpretation and ease of implementation.
2.
Feature importance analysis:
Feature importance analysis lets analysts identify the features most influential in the model’s predictions, clarifying which variables drive decision-making processes [38]. This approach enhances transparency and accountability by giving stakeholders insights into the factors shaping model outputs.
3.
Comprehensive model documentation
Detailed model documentation is essential, encompassing information on training data, hyperparameters, cross-validation methods, and performance metrics. Thorough documentation makes sure both analysts and end-users can evaluate the model’s validity and applicability, reducing risks of misinterpretation or misuse [39].
4.
Regulation testing for ethical compliance
To ensure compliance, models should be assessed for bias by testing for inadvertent prediction of sensitive features such as age, sex, or race. Documentation of these tests is essential to maintain ethical standards and regulatory alignment, reducing the risk of bias or illegal outcomes [40].

7. Statistical Software Integration

Integrating Python into Excel revolutionizes financial analysis by giving CFAs advanced tools for modeling and data-driven decision-making. Python’s powerful libraries, such as scikit-learn and TensorFlow, enable the creation of sophisticated predictive models directly in Excel, improving the accuracy of financial forecasts and valuation models. Statistical libraries like statsmodels and scipy offer deep analytical capabilities, surpassing Excel’s traditional functions, allowing for strong time series analysis, regression modeling, and hypothesis testing. Python’s speed and flexibility in executing Monte Carlo simulations enhance risk management and portfolio optimization, enabling CFAs to test scenarios and develop strategic insights. By combining Python’s computational power with Excel’s accessibility, CFAs can tackle complex financial challenges with greater precision and efficiency, transforming their approach to data analysis and decision support.

Risks

Excel’s evolution as an IDE for VBA has long helped with both low-code automation and complex application development within business environments. Recognizing the risks associated with VBA, EuSpRIG has long advocated for a robust programming methodology to mitigate errors and ensure consistent data integrity in financial applications [9]. Microsoft’s recent integration of Python as a supported language within Excel presents both opportunities and significant IT risks that require risk management.
On one hand, Python’s integration addresses certain risks commonly associated with open-source software by providing a managed environment with backward compatibility benefits that align with Microsoft’s support life cycle. This mitigates compatibility risks often present in decentralized Python deployments (McKinney, 2017) [41]. All the same, embedding custom Python functions directly into Excel cells adds substantial auditing complexity, especially since Python scripts introduce modularity and potential non-transparency in spreadsheet calculations. According to the COBIT® Framework, such changes demand expanded auditing protocols that incorporate comprehensive code review processes to validate both model integrity and function logic. Without this, there is a risk of errors propagating through critical financial analyses, particularly in sectors like asset management and insurance where model accuracy is paramount.
Managing these risks will require new controls for hybrid applications using both VBA and Python, which EuSpRIG best practices do not yet address. We should expand current practices to include structured code reviews, traditional software testing, and control frameworks for auditing and validation, in line with standards for multi-paradigm programming risks. For example, McKinney (2017) [41] highlights that consistency in function behavior across datasets is essential to maintain accuracy in complex calculations, suggesting a pressing need to standardize procedures across functions that leverage both Python and VBA. Frameworks for governance, like those in ISACA’s COBIT, will give these extended audit practices structure and help organizations deal with the higher IT risk that comes from using multiple programming languages simultaneously to create an Excel application.
Due to the complex architecture for applications embedding Python into Excel, new techniques for managing both the software audit risk and the function calculations are required. The governance of these applications will need to include traditional software testing techniques such as code reviews and test cases for cell functions that use Python libraries [42]. These changes will be essential for organizations aiming to maintain data integrity and accountability in a heightened risk environment.

8. Conclusions

Excel has evolved from a basic financial tool into a strong fintech platform, redefining how finance professionals approach automation and analysis. Excel now integrates Python and mL, empowering users to tackle advanced tasks like predictive modeling, portfolio optimization, and real-time data analysis. This transformation enables CFAs and finance professionals to develop sophisticated financial prediction models and applications using innovative mL techniques. By leveraging these advanced tools, they can unlock deeper insights, enhance decision-making, and address challenges like market forecasting, risk management, and portfolio optimization.
Excel’s new features put it back at the forefront of fintech, transforming it into a leading low-code analytics platform for advanced financial analysis. This transformation will let CFAs and other financial professionals create complex new financial forecasting applications using innovative ML techniques in a low-code environment. The advanced mathematics in these new financial applications should allow a portfolio manager to increase the portfolio’s risk–return ratio.
Yet these advancements come with increased responsibilities. As fintech relies on sophisticated analytics and real-time data, ensuring data integrity, security, and compliance is critical. To harness Excel’s potential while reducing operational risks, finance professionals must adopt the best rigorous practices in data governance, model validation, and audit processes. Excel’s new capabilities signal a future where finance and technology intersect more seamlessly than ever, but only with disciplined methodologies to maintain trust and accuracy.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

The data presented in this study are available in reference [33].

Conflicts of Interest

The authors report no conflicts of interest.

References

  1. Schmidt, P.J.; Riley, J.; Swanson Church, K. Investigating accountants’ resistance to move beyond Excel and adopt new data analytics technology. Account. Horiz. 2020, 34, 165–180. [Google Scholar]
  2. Benninga, S. Financial Modeling; MIT Press: Cambridge, MA, USA, 2014; Available online: https://books.google.com/books?hl=en&lr=&id=qRxWAwAAQBAJ&oi=fnd&pg=PR21&dq=excel+and+vba+financial+modeling&ots=7MeF4IIK7B&sig=ouTv6BeS5yAbzS_FnAlQaRA6224 (accessed on 7 February 2025).
  3. Samonas, M. Financial Forecasting, Analysis, and Modelling: A Framework for Long-Term Forecasting; John Wiley & Sons: Hoboken, NJ, USA, 2015; Available online: https://books.google.com/books?hl=en&lr=&id=XOYbBgAAQBAJ&oi=fnd&pg=PR13&dq=Excel+financial+modeling&ots=JFKt9zNYoU&sig=EkqxaetFqF17mb7MDQaGm6y7S2w (accessed on 7 February 2025).
  4. Winston, W. Microsoft Excel Data Analysis and Business Modeling; Microsoft Press: Washington, DC, USA, 2016; Available online: https://books.google.com/books?hl=en&lr=&id=ZbmPDQAAQBAJ&oi=fnd&pg=PT15&dq=%E2%80%A2%09Winston,+W.+L.+(2016).+Microsoft+Excel+data+analysis+and+business+modeling.+Microsoft+Press.&ots=HwgWdeZcYj&sig=VbYwgzfs7rEty_nIK0fcNaku1Gk (accessed on 7 February 2025).
  5. 13 Helpful Microsoft Excel Add-Ins for Data Analysis. Indeed Career Guide. 2024. Available online: https://au.indeed.com/career-advice/career-development/excel-add-ins-for-data-analysis (accessed on 7 February 2025).
  6. Marshall, C. Practical FinTech for Financial Professionals. Available online: https://www.gfmi.com/wp-content/uploads/2019/06/2019-Practical-FinTech-for-Financial-Professionals.pdf (accessed on 7 February 2025).
  7. Elserwy, T.B.; Raslan AT, N.E.-D.; Ali, T.; Gheith, M.H. Building Custom Spreadsheet Functions with Python: End-User Software Engineering Approach. J. Softw. Eng. Appl. 2024, 17, 246–258. [Google Scholar]
  8. Minerva. Will Excel Still Be Used by the FP&A Team of the Future? Minerva. Available online: https://minerva.com.au/will-excel-still-be-used-for-the-finance-team-of-the-future/ (accessed on 30 June 2021).
  9. Kumiega, A.; Van Vliet, B. Optimal Trading of ETFs: Spreadsheet Prototypes and Applications to Client-Server Applications. Interfaces 2008, 38, 289–299. [Google Scholar] [CrossRef]
  10. Montevechi, A.A.; de Carvalho Miranda, R.; Medeiros, A.L.; Montevechi, J.A.B. Advancing credit risk modelling with Machine Learning: A comprehensive review of the state-of-the-art. Eng. Appl. Artif. Intell. 2024, 137, 109082. [Google Scholar]
  11. Shi, S.; Tse, R.; Luo, W.; D’Addona, S.; Pau, G. Machine learning-driven credit risk: A systemic review. Neural Comput. Appl. 2022, 34, 14327–14339. [Google Scholar] [CrossRef]
  12. Bahrammirzaee, A.; Ghatari, A.R.; Ahmadi, P.; Madani, K. Hybrid credit ranking intelligent system using expert system and artificial neural networks. Appl. Intell. 2011, 34, 28–46. [Google Scholar] [CrossRef]
  13. Tajik, H.; Talebnia, G.; Vakilifard, H.R.; Ahmadi, F. Machine learning support to provide an intelligent credit risk model for banks’ real customers. Int. J. Nonlinear Anal. Appl. 2024, 15, 23–42. [Google Scholar] [CrossRef]
  14. Tola, V.; Lillo, F.; Gallegati, M.; Mantegna, R.N. Cluster analysis for portfolio optimization. J. Econ. Dyn. Control. 2008, 32, 235–258. [Google Scholar]
  15. Farid, F.; Rosadi, D. Portfolio optimization based on self-organizing maps clustering and genetics algorithm. Int. J. Adv. Intell. Inform. 2022, 8, 33–44. [Google Scholar]
  16. Issakainen, T. Clustering-based value investing strategy in the Helsinki Stock Exchange: K-means algorithm. J. Innov. Bus. Econ. 2023, 7, 115–128. [Google Scholar]
  17. Financial Modeling Institute. Scenario Analysis E-Paper; Financial Modeling Institute: Toronto, ON, Canada, 2022; Available online: https://fminstitute.com/scenario-analysis-epaper/ (accessed on 7 February 2025).
  18. Del Castillo Olivares, A.F.; Kumiega, A.; Sterijevski, G.; Van Vliet, B. An Empirical Study of Volatility Spillover Worldwide. Wilmott 2018, 2018, 48–59. [Google Scholar] [CrossRef]
  19. Podobnik, B.; Ivanov, P.C.; Grosse, I.; Matia, K.; Stanley, H.E. ARCH–GARCH approaches to modeling high-frequency financial data. Phys. A Stat. Mech. Its Appl. 2004, 344, 216–220. [Google Scholar]
  20. Madhuri, C.R.; Chinta, M.; Kumar, V.P. Stock market prediction for time-series forecasting using prophet upon arima. In Proceedings of the 2020 7th International Conference on Smart Structures and Systems (ICSSS), Chennai, India, 23–24 July 2020; pp. 1–5. Available online: https://ieeexplore.ieee.org/abstract/document/9202042/ (accessed on 7 February 2025).
  21. Sebesta, R.W. Concepts of Programming Languages; Pearson Education: London, UK, 2004; Available online: https://www.ime.usp.br/~alvaroma/ucsp/proglang/book.pdf (accessed on 7 February 2025).
  22. Aho, A.V.; Lam, M.S.; Sethi, R.; Ullman, J.D. Compilers: Principles, Techniques, and Tools; Addison-Wesley Longman Publishing Co. Inc.: Boston, MA, USA, 2006. [Google Scholar]
  23. Jackson, M.; Staunton, M. Advanced Modelling in Finance Using Excel and VBA; John Wiley & Sons: Hoboken, NJ, USA, 2006; Available online: https://books.google.com/books?hl=en&lr=&id=l0aAtPTVtJEC&oi=fnd&pg=PR3&dq=excel+and+vba+financial+modeling&ots=zEJUmgJyme&sig=51bLvtY_IgedsE-xUo8hibPwBm8 (accessed on 7 February 2025).
  24. Untwal, N.J.; Kose, U. Data Analytics for Finance Using Python; CRC Press: Boca Raton, FL, USA, 2025. [Google Scholar]
  25. Osipov, P.; Ziyatdinova, J.; Girfanova, E. Factors and Barriers in Training Financial Management Professionals. In The Challenges of the Digital Transformation in Education; Auer, M.E., Tsiatsos, T., Eds.; Springer International Publishing: Berlin/Heidelberg, Germany, 2020; Volume 916, pp. 167–175. [Google Scholar] [CrossRef]
  26. Murphy, S. Spreadsheet Hell. arXiv 2008, arXiv:0801.3118. [Google Scholar] [CrossRef]
  27. Chadwick, D. EuSpRIG TEAM work:Tools, Education, Audit, Management. arXiv 2008, arXiv:0806.0172. [Google Scholar] [CrossRef]
  28. O’Beirne, P. Information and Data Quality in Spreadsheets. arXiv 2008, arXiv:0809.3609. [Google Scholar] [CrossRef]
  29. Grossman, T.A.; Ozluk, O. Spreadsheets Grow Up: Three Spreadsheet Engineering Methodologies for Large Financial Planning Models. arXiv 2010, arXiv:1008.4174. [Google Scholar] [CrossRef]
  30. Mohseni, S.; Zarei, N.; Ragan, E.D. A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems. ACM Trans. Interact. Intell. Syst. 2021, 11, 1–45. [Google Scholar] [CrossRef]
  31. ISACA. Implementing and Continually Improving IT Governance; ISACA: Schaumburg, IL, USA, 2009; Available online: https://books.google.com/books?hl=en&lr=&id=2gwDIwXoVNoC&oi=fnd&pg=PA3&dq=isaca+data+governance&ots=zF26UOsVel&sig=SQ68HXL7Sek5L5ADihifbLzxpc8 (accessed on 7 February 2025).
  32. Ilori, O.; Nwosu, N.T.; Naiho, H.N.N. A comprehensive review of it governance: Effective implementation of COBIT and ITIL frameworks in financial institutions. Comput. Sci. IT Res. J. 2024, 5, 1391–1407. [Google Scholar] [CrossRef]
  33. Kuhn, M.; Johnson, K. Applied Predictive Modeling; Springer: New York, NY, USA, 2013. [Google Scholar] [CrossRef]
  34. Aguinis, H.; Gottfredson, R.K.; Joo, H. Best-Practice Recommendations for Defining, Identifying, and Handling Outliers. Organ. Res. Methods 2013, 16, 270–301. [Google Scholar] [CrossRef]
  35. Alexander, M. Excel Dashboards & Reports for Dummies; John Wiley & Sons: Hoboken, NJ, USA, 2022; Available online: https://books.google.com/books?hl=en&lr=&id=VyJiEAAAQBAJ&oi=fnd&pg=PA1&dq=microsoft+Excel+web+dashboards+&ots=Q3AC6tkYjC&sig=Twrv3EVB5KYXcTuftS4DQYY67gU (accessed on 7 February 2025).
  36. Kusleika, D. Data Visualization with Excel Dashboards and Reports. 2021. Available online: https://books.google.com/books?hl=en&lr=&id=PE4aEAAAQBAJ&oi=fnd&pg=PR21&dq=microsoft+Excel+web+dashboards+&ots=zIsd1j5pHg&sig=XCBWALRPfZ4qc5CF6i5t9mG9p4o (accessed on 7 February 2025).
  37. Rudin, C.; Chen, C.; Chen, Z.; Huang, H.; Semenova, L.; Zhong, C. Interpretable machine learning: Fundamental principles and 10 grand challenges. Stat. Surv. 2022, 16, 1–85. [Google Scholar] [CrossRef]
  38. Saarela, M.; Jauhiainen, S. Comparison of feature importance measures as explanations for classification models. SN Appl. Sci. 2021, 3, 272. [Google Scholar] [CrossRef]
  39. Linardatos, P.; Papastefanopoulos, V.; Kotsiantis, S. Explainable ai: A review of machine learning interpretability methods. Entropy 2020, 23, 18. [Google Scholar] [CrossRef] [PubMed]
  40. Agnello, V.; Kumiega, A. Machine Learning, Law, and Ethics: The Discrimination Problem and Solution. Bus. Prof. Ethics J. Forth Coming 2024. [Google Scholar]
  41. McKinney, E., Jr.; Yoos, C.J., II; Snead, K. The need for ‘skeptical’accountants in the era of Big Data. J. Account. Educ. 2017, 38, 63–80. [Google Scholar] [CrossRef]
  42. Kumiega, A.; Van Vliet, B. Quality Money Management: Process Engineering and Best Practices for Systematic Trading and Investment; Academic Press: Cambridge, MA, USA, 2011; Available online: https://books.google.com/books?hl=en&lr=&id=Mjd96ayZ98kC&oi=fnd&pg=PP1&dq=Andrew+Kumiega&ots=TmrJKF5VDb&sig=u7uVmyB2nXILVyLaG0WkowKDdJ8 (accessed on 7 February 2025).
Fintech 04 00014 g001
Figure 1. A partial representation of the Excel object framework.
Figure 1. A partial representation of the Excel object framework.
Fintech 04 00014 g001
Table 1. .Data Science Applications in Excel.
Table 1. .Data Science Applications in Excel.
Sub-SectionToolTool Functions
Data managementPower QueryGet and transform dataIt facilitates the establishment of connections with databases, text files, workbooks, and online services.
Data managementPower QueryQuery Editor Interfaces transforming and cleaning data.
Data ManagementPower QueryPower Query Formula LanguageThe M Language is a functional language for both Excel and Power BI. It allows for complex manipulation of data in Power Query.
Data Management and Data ShapingPower Pivot TabDiagram ViewLets users view, create, and change relationships in a graphical format, making it easier to understand the structure of the data model.
Data ShapingAdvanced FilterFilteringAdvanced Filter: This tool offers more sophisticated filtering options, letting users specify complex criteria for extracting data from a dataset.
Data ShapingAdvanced FilterSlicingSlicing lets analysts analyze small portions of the data.
Data Shaping/Business AnalyticsPower Pivot TabPower PivotPower Pivot is an OLAP-style tool that lets analysts quickly summarize data. Power Pivot also lets analysts create pivot graphs, which lets management quickly understand the data.
Business Analytics and IntelligencePower Map TabPower MapPower Maps enables users to plot data points on maps, visualize trends, patterns, and relationships, and gain insights into geographic datasets.
Business Analytics
And Intelligence		Data TabData Analysis ToolPakThis is the original data analysis tool. It provides a range of statistical and analytical tools to perform data analysis tasks such as regression analysis, histograms, and more.
Business Analytics
And Intelligence		Data TabSolver Solver lets an end user perform linear and non-linear optimization.
Business Analytics
And Intelligence		Data TabAdvanced Solver/XLMinerAdvanced Solver helps with various data analysis and predictive modeling tasks, including regression analysis, classification, clustering, decision trees, random forests, and forecasting.
Business Analytics
And Intelligence		NeurosolutionNeurosolutionNeurosolution allows for predictions using neural networks.
Business Analytics
And Intelligence		@Risk Tab@RiskAdvanced simulation software that allows for Monte Carlo-based Risk models
Business Analytics
And Intelligence		SAS Add-inSAS TabIt enables the complete integration of SAS features into Excel.
ProgrammingDeveloper TabVBAExcel VBA enables users to automate Excel processes and create intricate custom calculations.
ProgrammingPythonPythonExcel Python enables advanced data analysis, visualization, and automation using Python libraries within the Excel environment by integrating Python directly into Excel.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Kumiega, A. Automated Ledger or Fintech Analytics Platform? FinTech 2025, 4, 14. https://doi.org/10.3390/fintech4020014

AMA Style

Kumiega A. Automated Ledger or Fintech Analytics Platform? FinTech. 2025; 4(2):14. https://doi.org/10.3390/fintech4020014

Chicago/Turabian Style

Kumiega, Andrew. 2025. "Automated Ledger or Fintech Analytics Platform?" FinTech 4, no. 2: 14. https://doi.org/10.3390/fintech4020014

APA Style

Kumiega, A. (2025). Automated Ledger or Fintech Analytics Platform? FinTech, 4(2), 14. https://doi.org/10.3390/fintech4020014

Article Metrics

Back to TopTop