Data analytics for Loan Club investment BE883 Assignment Sample
Introduction
In the mentioned article, “Data analytics for Loan Club investment“, a piece of detailed information about a professional young woman looking for the diversification of her profile. From analysing the woman’s educational background, it was found that she underwent a master degree in the “Data Science Program”. Her professional portfolio was further glorified by the tech company’s four years of experience as a product manager. She also saved a good amount of goodwill, and she is willing to invest the amount in the more diverse field apart from the traditional investment schemes like stocks and bonds. She is now considering “peer-to-peer loans“ available via online platforms as an asset. Through her knowledge from the data science field, she analyses the lucrative investment schemes offered by those “peer-to-peer loans“ organisations. This article focuses on shedding some light on the few questions that may seem beneficial for Triss on her way to invest in those schemes (Bachmann et al. 2017).
Discussion
Question 1.
While investing in “peer-to-peer loans,” there are few factors which must be considered.
Consumer Capacity: The capacity of the regular and potential consumer can be considered to be worth exploring before investing in the “peer-to-peer loans“ organisation. As most of the loans are provided to the consumers in a small amount and for a short duration. There is a potential risk of non-payment from the customer. In that case, her money can become stagnant for a considerable amount of time. So before investing in the organisation Triss must check the background and the customer niche of that organisation (Alomari, Z. and Fingerman, D., 2017).
Biasness of The Industry: The industry is often painted in dull colour for their investor to client transparency. Often the personal information of the clients is set to be anonymous for the investor. This causes a lack of available data for the investors. The investors can only have information about the credit score. As with all the investors, Triss will be tempted to invest in high-risk clients as it can increase the amount of money on return. But this will increase the potential risk of repayment for Triss. So it is advised to Triss get some general ideas apart from the data analytics available before investing in the organisation (Gavurova et al. 2018).
Conduct her own research before lending: The credit system in the “peer-to-peer loans” organisation is generally provided by the agencies, so there is a potential chance of data fraudulency as the agencies are not bound to properly survey the background information of the customer before assigning them with credit. So Triss has to perform her own research before providing a loan to a client (Gao, J., Martin, X. and Pacelli, J., 2017).
Question 2.
From analysing the journal, it was found that Triss has a good amount of goodwill and. So her objectives can be
Try diversifying her investor portfolio.
To earn more money in a shorter amount of time. As most of the loans are provided for 1 to 3 years, the time for waiting is relatively low. And the return rate is dependent on the credit score of the potential client. The high-risk client can provide a good amount of money in return.
To get accustomed to the non-traditional source of income. As it is known, due to the global pandemic, the equity of the market shares is quite downfacing. So it will be beneficial for Triss to further increase her goodwill by investing in “peer-to-peer loans“.
The investors’ decision-making capabilities can be proven to be crucial for her. There are two sets of decision-making terms popular in the investment market. The “Good Decision” and “Bad Decision”. There is no such universally accepted term to get the definition of those two terms. Colloquially speaking, the line which separates the “Good Decision” from the “Bad Decision” is the repayment of loans from the customer. From the investor’s point of view, “Good Dicison” can be invested in the clients who will provide repayment at the proper time. The risk in this type of investment is quite low. The “Bad Decision” may be lending money to the clients, which may cause the stagnancy of return for a longer period of the term. This type of investment can be termed as a high-risk investment (Alexandrov, A. and Jiménez, D., 2017).
Question 3.
By analysing the past data of the organisation from which Triss is willing to conduct her lending activities, Triss can get enlightened with the customer niche and their requirements. Triss can also get a detailed view of the time to be invested before getting the repayment. Triss can also be provided with information about the default rate of the organisation. As the personal information of the potential client is hidden so Triss must be dependent on the organisation for acquiring data about her potential clients. The past data can also shed lights on the correlation of two variables on the “peer-to-peer loans “market (Chen et al. 2020).
Triss could use some help by analysing past data. The past data would provide her default rate that the investor faced while lending money via that online platform. Apart from this, the past data can help Triss to get an idea about the potential customers and their cause of needs. Triss can also get helped from the past data to get some insights about the average waiting time before getting a repayment. Triss by proper analysis of the data may get some ideas about the weight age of loans provided to the buyers by that platform. The previous data also can provide data on the residential zip codes of the previous clients of the platform. This will help Triss to get the demography of the operation of the company. The previous data also provide some ideas about the purpose for which the previous clients opted for applying for a loan on the organisation (Tanawong et al. 2020).
Question 4.
The categorisation of the different attributes associated with the loans is important for the purpose of short listing the most important attributes to facilitate her decision before nodding her head for lending the money to the client. Triss, as a young investor, is willing to take the risk to maximise the amount of money during the repayment. At the same time, analysing the past data Triss at first categorised data mashed on their alphabetical nature. By doing that, Triss gets an idea about the issue date and the potential risk of the client, which operates via that organisation. By categorising data on the alphanumeric ground, a detail about the data of lending and the date of repayment have been obtained by Triss. The numerical analysis provided Triss with valuable information about the weightage of money which is invested in the lending purpose and the amount of money obtained during the process of repayment. The ups and downs of the market are also categorised under this group (Escalante et al. 2018).
The principal objective of Triss was to get maximum repayment, as it is mentioned in the article that Triss was able to save a good amount of fortune for the future of her investment portfolio. So, it is easy to assume that the availability of capital for lending is not a matter of concern for her. Triss is looking for earning money, and she is willing to take some calculative risk for that purpose. So, it will be fair to assume that Triss is not afraid of taking the risk. There is no intention for Triss to get details about the buyer’s reason for taking the loan. So it can be fair to say that Triss may remain ignorant about the personal details of her potential client. Triss is more interested in the total repayments attribute while analysing the datasheet of the organisation (Avarikioti et al. 2018).
Question 5.
The total amount payable is used to get the information about the amount of the money which has to be repaid by the buyers to the lending organisation or, in this case, to the peer at the end of the lending period agreed during the process. The total amount payable has a strong correlation with the present status of the loan as it is seen while analysing the past data it was found that the loans which have low repayment amount during the end of the time tend to get paid on time and often before that. But the repayment procedure gets slightly worrisome for the loans where the repayment amount is quite a big number. The buyers seem to delay the time of repayment, and also, there is a chance of default in those cases. So the risk in those accounts is quite high (Sedjati et al. 2018).
According to the marketing experts, there is no connection between the correlation of the variable with the data redundancy. The process of applying and granting loans are highly interrelated. This interrelation of the variables makes the process more stable, and one can have some idea about the nature of one variable by simply looking at the other variable. For example, one can get an idea about the risk status of the loan by just simply looking at the credit score of the buyer. The time period and the interest rate helps in the finding of the net amount payable at the time of closure. This net amount payable again sheds light on the loan status as it is discussed above (Dzwigol et al. 2019).
Question 6.
The methods that Triss followed during her process of collection and analysation of data are as follows;
- At first, she assessed her needs. And tried to collect data which suits most according to her needs.
- Then she draws that data according to the objectives she steed up before joining this investor field.
- Then she identifies her sources for acquiring the information and starts to harvest than for collecting the information.
- Then she identified her “Key performance indicator (KPI)“. This helped her to get insights into the capabilities of the company to perform its key points.
- To reduce the complexities of the data, she identified useless attributes like the gender of the buyer and neglected them while designing the datasheet.
- By constructing a roadmap for the data analysis, she sped up the process of analysis of the data. This helped her to reduce the time and complexity of the research.
- By applying softwares like “MS Excel” and other software designed for the statistical analysis of data. Tiss reduces the chances of error and avoids the complexities caused because of the calculation of the data.
- By analysing the processed data, Tiss is now able to have some ideas about how to proceed in the field.
There were the same old traditional tasks performed by Tissa to analyse the data.
- At first, Tissa went for the descriptive analysis of the dataset to get information about the operational strategies and figures of the online platform.
- Then by the process of diagnostic analysis, Tissa was able to get some causative agents for the facts and figures she collected.
- Then with the help of the predictive analysis, Tiss assessed her scope in the “peer to peer loans” market (com, 2021).
Question 7.
For facilitating her need, Tiss broke down the process of data mining into six different stages.
Understanding The Business
This step has been regarded as the initial and the most important stage for the purpose of data mining. In this stage, Tiss acquired the ins and outs of the “peer to peer loans” market. She also identified the source of necessary resources.
Understanding The Data
In this phase, Tiss started her journey to explore the data and gained familiarity with them. This helped Tiss to sort out the appropriate tools and algorithms which will prove to be useful in the modelling phase of data.
Preparing The Data
This is considered the most important phase for the mining of data. In this stage, they are processed for analysis and further mining. In this stage, Triss mergers and aggregated the data she acquired while collecting the data.
Data Modeling
In this phase, Triss applied a different modeling algorithm on the sets of data. This selection process of algorithms is related to the nature of the data. These algorithms helped Trissa with the proper analysation and the sorting purpose (researchgate.net, 2021).
Evaluating the Data
In the process of evaluating the data, the data was put under scrutiny, and the accuracy of the data is determined. The accurate data can now be used in the process of fulfilling the objective set by Tissa.
Question 8.
The selection of the model is one of the basic tasks for every analysis. The techniques for the selection of the model can be considered as the estimates of some physical quantities. There is the immense importance of biasness and variance of data while opting for a specific model of data analysis. The selection of models for analysis is made by considering some factors like the rate of error that can happen by undergoing that mode, the reduction of complexity of data that can be achieved and the scope of cross-validation of the data that is obtained by using the models. Tissa has created many models. From them, she filtered out the model that best suited the operation. Naturally, she opted for the model, which will provide the most accurate data and analysis for the project. Tissa opted for the model which will suit purpose her. But the datas obtained by both the models are similar in nature, so the selection of the model is made to reduce the complexity of the data collection (ieeexplore.ieee.org).
Question 9.
The stability of the model can be an important attribute while assessing the future scope of the table. The stability of the data model can be best described as the data model, which can facilitate the analysis at every stage. A stable model has low data redundancy. A stable data model always remains stable no matter addition and the deletion of the data at the later stage of data analysis. To analyse the stability of the model, Triss checks her model by using two different metho. She first checks the viability of the model. She re-fit the model by including different data sets and variable attributes. She found that the model remains stable throughout the process. Then she further analyse the module by using a test data set (onlinelibrary.wiley.com, 2021 ).
Conclusion
From reviewing the article, it was found that Triss is willing to undertake risk for generating fortune by investing in the “Peer to peer loans“. While analysing the operating structure of the business, it was found that the operation is carried out by the process of systematic lending and repayment between investors and clients. Though the higher return can be obtained by Trissa by investing upon the higher risk time. In the business, it was found that the variables are often correlated with each other. Like the increase in the net payment may result in the delay of the repayment status. By analysing the financial data of the desired organisation Triss found out that that investing in the clients of this platform is quite safe as 94% of the loans get repayment by the client. The organisation is also well structured; they are noted to generate a handsome revenue of over $10 billion. So it would be safe to say that the young professionals who want top diversify their investment portfolio like Triss may opt for the “peer to peer loans”.
Reference List
Journal
Bachmann, A., Becker, A., Buerckner, D., Hilker, M., Kock, F., Lehmann, M., Tiburtius, P. and Funk, B., 2017. Online peer-to-peer lending-a literature review. Journal of Internet Banking and Commerce, 16(2), p.1.
Alomari, Z. and Fingerman, D., 2017. Loan Default Prediction and Identification of Interesting Relations between Attributes of Peer-to-Peer Loan Applications. New Zealand Journal of Computer-Human.
Gavurova, B., Dujcak, M., Kovac, V. and Kotásková, A., 2018. Determinants of successful loan application at peer-to-peer lending market. Economics & Sociology, 11(1), pp.85-99.
Gao, J., Martin, X. and Pacelli, J., 2017. Do loan officers impact lending decisions? Evidence from the corporate loan market. Unpublished working paper.
Alexandrov, A. and Jiménez, D., 2017. Lessons from bankruptcy reform in the private student loan market. Harv. L. & Pol’y Rev., 11, p.175.
Liu, J., Fang, M., Jin, F., Wu, C. and Chen, H., 2020. Multi-attribute decision making based on stochastic DEA cross-efficiency with ordinal variable and its application to evaluation of banks’ sustainable development. Sustainability, 12(6), p.2375.
Tanawong, T., Khruahong, S. and Roongrungsi, A., 2020. The Performance Comparison of Models for Predicting the Risk of Losing Student Loan by Fuzzy Neural Network Method and Multiple Linear Regression Analysis Method. Naresuan University Journal: Science and Technology (NUJST), 28(2), pp.81-93.
Escalante, C.L., Osinubi, A., Dodson, C. and Taylor, C.E., 2018. Looking beyond farm loan approval decisions: Loan pricing and nonpricing terms for socially disadvantaged farm borrowers. Journal of Agricultural and Applied Economics, 50(1), pp.129-148.
Avarikioti, G., Laufenberg, F., Sliwinski, J., Wang, Y. and Wattenhofer, R., 2018. Towards secure and efficient payment channels. arXiv preprint arXiv:1811.12740.
Sedjati, D.P., Basri, Y.Z. and Hasanah, U., 2018. Analysis of Factors Affecting the Payment of Zakat in Special Capital Region (DKI) of Jakarta. International Journal of Islamic Business & Management, 2(1), pp.24-34.
Dzwigol, H., Aleinikova, O., Umanska, Y., Shmygol, N. and Pushak, Y., 2019. An entrepreneurship model for assessing the investment attractiveness of regions. Journal of Entrepreneurship Education, 22, pp.1-7.
Online Article
mdpi.com, 2021 LOAN CLUB INVESTMENT Available at: https://www.mdpi.com/2227-7390/7/9/846/htm [ Accessed on : 10/03/2021]
researchgate.net, 2021 LOAN CLUB INVESTMENT Available at: https://www.researchgate.net/publication/325981679 [ Accessed on : 10/03/2021]
ieeexplore.ieee.org, 2021 LOAN CLUB INVESTMENT Available at: https://ieeexplore.ieee.org/abstract/document/8338177/ [ Accessed on : 10/03/2021]
Website
onlinelibrary.wiley.com, 2021 LOAN CLUB INVESTMENT Available at: https://onlinelibrary.wiley.com/doi/abs/10.1002/for.2625
[ Accessed on : 10/03/2021]
Know more about UniqueSubmission’s other writing services:
