FINM4100 Analytics in Accounting, Finance and Economics Assignment 3 Sample

FINM4100 Analytics in Accounting, Finance and Economics. Ass 3

Finance – Assignment Writing

Your Task

Create a slide deck which represents a portfolio of analytics methods used in accounting, economics or finance. This task is to be done individually. Submit your slides at the end of class via MyKBS.

Assessment Description

Learning Outcomes: LO2, LO3, LO4 and LO5

Assessment Instructions

As an individual:

• You will choose five analytics methods and a financial, accounting or economics application for each method.

• Out of the five methods that you chose, you are required to investigate one in more detail.

• Reflect on the limitations of the methods and possible ethical, legal or privacy issues.

Refer to the assessment marking guide to assist you in completing all the assessment criteria.

This will be provided closer to the due date in conjunction with the Assessment Webinar 

Solution

Introduction

● Data analytics and its application in finance, and accounting have accelerated the industry and resulted in increased competition in the market.

● The generation of more than 2.5 quintillion bytes of data makes it crucial for data extraction for enhancing strategic decisions undertaken by businesses. 

● The usage of Predictive data analytics by accountants has resulted in gaining meaningful insights and assisting in effective risk management.

In the current industrialization era, almost all sectors are driven by big data. Data analytic usage within accounting, finance, and economics has become vital for monitoring corporate performance, enhancing client experiences, generating increased profit margins, and effectively identifying risk. As per the MBA Assignment Expert overview, Furthermore, the implementation of advanced data analytics within the business models helps accounting firms to stay ahead of the competition. 

Analytics method 1: Association rule learning

● "Association rule learning" is an "unsupervised" learning technique used to find data patterns within a given data set (Fan et al. 2019). 

● If-then patterns are widely searched for creating association rules and relying upon confidence and criteria support for identifying relationships among data elements.

● The frequency of appearance of if-then within data is determined by support while confidence denotes the number of times the "if-then" statement appears to be valid.

Association rule utilizes machine learning for analyzing data patterns as well as their co-occurrence within the database. Antecedent (if) as well as consequent (then) are included within the association rule.  Support along with confidence determines the strength of the "association rule."
Application

● Utilization of Association rule learning by accountants and financial experts provides them with unprecedented opportunities for undertaking informed decisions. 

● The method is used by retail users in banking services to recognize the patterns of likelihood among users to purchase the services (Fan et al. 2022).

● The association of the availability of data patterns from "market basket databases" can further help in cross-marketing and catalog designing. 

Association rule mining techniques assist the accounting, and finance industry in identifying patterns, correlations, and patterns within databases. Items brought on credit cards for instance like rental cars provide information about the likelihood of purchasing items by consumers. Furthermore, the application of the Association rule helps in fraud detection, customer acquisition, and the provision of suggesting segment-based products for better customer targeting. 
Analytics method 2: Classification tree analysis

● "Classification Tree Analysis" is the analytical procedure that relies upon training data for constructing decision trees depending upon measured attributes. 

● A decision tree is simple and easy to interpret and helps decision-makers predict outcomes based on varied circumstances (Huang et al. 2020).

● Uncertain values within the decision tree often result in uncertain outcomes and complicated calculations.

The "Binary recursive partitioning" method is used for the construction of classification trees that split data into several partitions. The benefits of decision trees further highlight that they can be combined with several decision techniques. The instability of decision trees can result in large structural changes. Furthermore, bias and inaccuracy are some of the major drawbacks of decision trees. 
Application

● The decision tree showcases events and decision sequences that affect project risk and cash flow (Pallathadka et al. 2023). 

● Decision trees assist managers in visualizing uncertainties and trade-offs included within a project and varied alternatives are compared by relying upon probabilities and expected values. 

● Decision trees help investors in accurately evaluating bonds.  

Nodes of trees represent uncertain events while branches denote possible outcomes. Decision tree is further used in case of option pricing. "Binomial option pricing model" utilizes discrete probabilities for determining values of "option at expiration". Assumptions of binomial models indicate an increase or decrease in the underlying value of the assets based on calculated probabilities at the time of maturity. Increases as well as decreases in interest rates have widespread consequences on interest rate derivatives. Investors can make better decisions based on uncertainties associated with future areas of interest.
Analytics method 3: Genetic algorithms

● A genetic algorithm is a method used for resolving unconstrained, constrained optimization problems by utilizing the power of nature (Ghoddusi et al. 2019).

● A genetic algorithm is used for the prediction of security prices utilized by traders for trading rules optimization through the identification of suitable values to be used for security. 

● Vectors are used for creating genetic algorithms.

Genetic algorithms mimic natural selection procedures. The concept of natural selection is used by these techniques for identifying reliable solutions for complications. Parameters of the trading rule are represented through "one-dimensional vectors" which are often treated as "chromosomes" in the context of genetic terms. GS is utilized as an optimizer that adjusts parameters for maximizing or minimizing feedback measures and is further utilized independently for ANN construction. 

Application

● Genetic algorithms are used for making predictions in financial markets.

● GA is utilized for investment management by predicting return on varied assets (Drachal and Pawłowski, 2021)

● Genetic algorithms are much more rapid, convenient, and efficient in resolving financial portfolio challenges.   

Genetic algorithms hold numerous potentialities within the financial industry through forecasting returns, portfolio optimization, and discovery of trading rules. GA has been successfully utilized for predicting relative return on individual shares that serves to be beneficial in "strategic share allocation". In investment management, it is important to identify the appropriate weight given to individual securities in the case of the portfolio. In such cases, GA proves to be effective for the optimization of an investment portfolio. 

Analytics method 4: Machine learning

● Machine learning is a form of AI that emphasizes algorithm creation and enables machines to obtain insights from historical data (Yang, L. and Shami, 2020).

● Prediction models are built by ML that learn from existing data and predict the outcome

● It is widely used for data visualization and analysis based upon which industries can make informed decisions. 
Machine learning emphasizes the usage of statistical techniques to enable computers to make informed decisions without being explicitly programmed. Ml algorithms are specifically used for pattern detection, data clustering, identifying data outliers, and making forecasts based on future data. 
Application

● ML is utilized in the finance industry for risk management, fraud detection, customer support, and algorithm trading. 

● ML is widely used for financial forecasting that drives effective investment decisions. 

● Fraudulent activities can be easily determined and detected through the usage of ML within fintech companies and freezing suspicious activities to minimize loss (Ray, 2019). 

Finance organizations are associated with handling billions of dollars across the world, resulting in the generation of large volumes of data required for obtaining valuable insights. Thus application of ML within financial organizations serves to be effective in strengthening security and reducing risk levels. Ml also assists in the financial portfolio management of the investors. The online application utilizes algorithms to look at investments and optimize customers' assets about financial goals and risk preferences. 

Analytics method 5: Regression analysis

● Regression analysis is the statistical method utilized to indicate the interrelationship between two or more variables (Demir et al. 2022).  

● Regression analysis helps investor managers identify relationships between business stock and commodity prices. 

● Regression analysis is a reliable method and performs effectively for linearly separable data.

Regression analysis is widely used in investment and finance departments for identifying the relationship existing between independent and dependent variables. Regression analysis is one of the powerful tools utilized for uncovering links between variables observed within data but fails to indicate causation. Regression analysis is easy to implement and can be effectively trained to obtain valid outcomes. 

Analytics method 5: Regression analysis

● Regression analysis helps in identifying factors impacting data insights.

● Simple linear regression focuses on defining relationships between variables through “coefficients of the linear equation” estimation (Nizam et al. 2022).

● Multiple regression uses more than one "predictor variable" for describing response variables. 

Regression analysis can be used to determine factors that play a significant role in generating outcome and their significance. In simple linear regression, the "corresponding predictor variable" present in the response variable affects the value.  Simple regression often fails to explain connections existing between data. In case of complicated data connection, "multiple linear regression " is used. 
Application

● In financial modeling, regression analysis is used for estimating the strength existing between variables and predicting their future behavior (Okafor et al. 2021). 

● Regression analysis and the "Capital Asset Pricing Model "go hand in hand. 

● Regression analysis is used in preparing financial statements of the organization.

CAPM is used for determining the relationship between “associated market risk premium’ and expected return on assets. Regression analysis is used for predicting sales of the organization and usage of the model indicates conduction of prediction based on previous data.  
Analytics method and its limitation

● Data analytics are not always flawless. 

● Data quality, assumption, data interpretation, and sample size are some of the limitations of data analytics (Dai et al. 2020).

● The limitation of predictive analytics indicates that it relies upon past data and not data retrieved from the future.

Data analytics are crucial for implementing informed decisions through resolving complicated problems. Limitations exist in all data analytics that can affect the quality of the data obtained. The limitation of data analytics affects the reliability and viability of the results obtained. Limitations existing within data analytics should be effectively communicated to maintain honest transactions.  Results obtained in the case of predictive analytics remain doubtful. 

Privacy, legal and ethical issues

● It is extremely crucial to maintain ethical, and legal standards while conducting data analysis. 

● Ethical standards highlight the maintenance of accuracy and quality of data obtained (Martin, 2020).

● Data accumulated through data analytics are not to be misused, indicating adherence to data privacy. 

Conduction of data analytics through the usage of ethical standards enhances the reliability of the data. Data quality ensures the wellness of the outcome in depicting the reality of the situation. Such information proves beneficial in undertaking valid information. Privacy issues emphasize that data collected should be misused and confidentiality should be maintained. 

Conclusion

● Data analytics are widely used in several disciplines for reaping the benefits of predictive outcomes.

● Data analytics helps investors, and financial personnel to make informed decisions.

● Data should be ethically accumulated for betterment.

Data analytics has opened up new opportunities for business organizations to implement adequate actions that would contribute toward the organization's productivity. 

References

Dai, H.N., Wang, H., Xu, G., Wan, J. and Imran, M., 2020. Big data analytics for manufacturing internet of things: opportunities, challenges and enabling technologies. Enterprise Information Systems, 14(9-10), pp.1279-1303.

Demir, A., Pesqué-Cela, V., Altunbas, Y. and Murinde, V., 2022. Fintech, financial inclusion and income inequality: a quantile regression approach. The European Journal of Finance, 28(1), pp.86-107.

Drachal, K. and Pawłowski, M., 2021. A review of the applications of genetic algorithms to forecasting prices of commodities. Economies, 9(1), p.6.

Fan, G., Shi, W., Guo, L., Zeng, J., Zhang, K. and Gui, G., 2019. Machine learning based quantitative association rule mining method for evaluating cellular network performance. IEEE Access, 7, pp.166815-166822.

Fan, W., Fu, W., Jin, R., Lu, P. and Tian, C., 2022. Discovering association rules from big graphs. Proceedings of the VLDB Endowment, 15(7), pp.1479-1492.

Ghoddusi, H., Creamer, G.G. and Rafizadeh, N., 2019. Machine learning in energy economics and finance: A review. Energy Economics, 81, pp.709-727.

Huang, J., Chai, J. and Cho, S., 2020. Deep learning in finance and banking: A literature review and classification. Frontiers of Business Research in China, 14(1), pp.1-24.

Martin, K.E., 2020. Ethical issues in the big data industry. In Strategic Information Management (pp. 450-471). Routledge. 
Nizam, R., Karim, Z.A., Rahman, A.A. and Sarmidi, T., 2020. Financial inclusiveness and economic growth: New evidence using a threshold regression analysis. Economic research-Ekonomska istraživanja, 33(1), pp.1465-1484.

Okafor, A., Adeleye, B.N. and Adusei, M., 2021. Corporate social responsibility and financial performance: Evidence from US tech firms. Journal of Cleaner Production, 292, p.126078.

Pallathadka, H., Ramirez-Asis, E.H., Loli-Poma, T.P., Kaliyaperumal, K., Ventayen, R.J.M. and Naved, M., 2023. Applications of artificial intelligence in business management, e-commerce and finance. Materials Today: Proceedings, 80, pp.2610-2613.

Ray, S., 2019, February. A quick review of machine learning algorithms. In 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon) (pp. 35-39). IEEE.

Yang, L. and Shami, A., 2020. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415, pp.295-316.