Module Name Credit Risk and Financial Analytics
Module Code ACCN 303
Lecturer Mr E. Mundingi
Assignment 2
GROUP MEMBERS
SURNAME NAME REGISTRATION NUMBER
1.MUSEKIWA ROSELINE R232714N HACCN
2.DENGA DELAN T R233269R HFET
3.CHISASA ROGERS S R233257R HFET
4.MUKWADA TADIWANASHE R233270W HFET
5.DHARINGO TADIWANASHE R236751G HFET
6.DENGA DENZEL T R233267Q HFET
7.TEMBO BRENDON R214429H HFET
8.CHIKOWORE GUYLORD A R214486S HFET
9.DZAPASI WINFILDER L R214498L HFET
10.DUMUKWA FARAI R236427J HFET
11.MAROWA OTIS R214432X HFET
12.MUROZA PRIDE R214496U HFET
13.MBIZO TINASHE C R214454P HFET
14.MUKWENGA ESTERY R238139M HACCN
15.MAKANDIONA ABIGAIL R238136A HACCN
16.KATIVHU CHRIS R233258X HFET
QUESTION 3
Question 4
You want to analyze the profitability of default of SMEs in Zimbabwe to be able to mitigate
losses, evaluate the significance of the following 4 main types of data analytics highlighting
where you would obtain the data from
1. Descriptive analytics
2. Diagnostic analytics
3. Predictive analytics
4. Prescriptive analytics
The probability of default of Small and Medium Enterprises (SMEs) in Zimbabwe refers
to the likelihood that an SME will be unable to meet its financial obligations, particularly
the repayment of loans, as they come due over a specific period. It is a crucial measure of
credit risk associated with lending to or investing in SMEs.
1. Descriptive Analytics
Deals with summarizing of historical data to identify trends, patterns, and key characteristics of
SME defaults. This involves looking at past default rates, the types of SMEs that have defaulted,
the timing of defaults, and basic financial indicators leading up to default. Significance of
descriptive analytics include, business intelligence (to analyze historical data and identify trends)
Data sources for descriptive analytics include Financial Institutions (commercial banks,
microfinance institutions), Credit Bureaus, Reserve Bank of Zimbabwe, Government agencies eg
Ministry of Finance, Economic Development and Investment, SMEs Associations the likes of
National Venture Capital Company of Zimbabwe. These examples may have Internal historical
data on SME loan portfolios, including loan performance (repaid, delinquent, defaulted), SME
characteristics (sector, size, age), and financial information provided during loan applications and
ongoing monitoring. Research indicates that borrower SME records and financial statements
from financial institutions are paramount for examining SME default risk, Aggregate data on
non-performing loans (NPLs) within the banking sector, potentially segmented by SME lending.
The RBZ also conducts surveys and collects financial sector data.
2. Diagnostic Analytics
This deals with investigating the reasons behind historical defaults by identifying correlations
and causal factors. This model also helps in quality control, identifying defects and lastly supply
chain optimization. This involves analyzing the relationship between various financial and non-
financial variables and the occurrence of default and the key questions include, what were the
primary financial distress indicators that preceded SME defaults (e.g., declining profitability,
increasing debt burden, poor cash flow)? How did macroeconomic factors (e.g., inflation,
exchange rate volatility, GDP growth) contribute to SME defaults? Did specific firm
characteristics (e.g., management experience, business model, access to markets) play a
significant role and the economic conditions which rendered the default? Data sources for
diagnostic analytics include, Economic Data from RBZ and Zimbabwe National Statistics
Agency (ZIMSTAT). These examples may include Time series data on inflation rates, interest
rates, exchange rates, GDP growth, sector-specific performance, and other macroeconomic
indicators. Trading Economics also provides Zimbabwe's economic indicators.
3. Predictive Analytics
Its main focus is developing models to forecast the probability of default for current SMEs based
on historical patterns and identified risk factors. This model also has the following active actions
that is, forecasting (forecasting future events and trends) and also risk management (identifying
possible risks and opportunities) . This involves using statistical techniques and machine
learning algorithms to build credit scoring models. The key questions no include, Which SMEs
in the current portfolio are at the highest risk of default? What are the key predictors of SME
default in the current economic environment? Data Sources include historical Data on SME
Defaults (as used in descriptive and diagnostic analytics, but now used to train predictive
models), macro-economic forecasts that is the IMF, World Bank, African Development Bank and
the RBZ
4. Prescriptive Analytics
This model aims on Recommending specific actions or strategies to mitigate the risk of SME
defaults and minimize potential losses. This involves using the insights from predictive analytics
and considering various scenarios and potential interventions. It also includes decision making in
a business and the efficient allocation of resources and this is resource efficiency allocation). The
questions which are pivotal include, what proactive measures can be taken to reduce the
likelihood of default for high-risk SMEs (e.g., restructuring loans, providing business
development support, offering financial literacy training)? What are the optimal lending policies
and risk management strategies for the SME sector in Zimbabwe? The examples for where to
obtain the data include Insights from Predictive Analytics (factors that had the most impact on
probability default) and also Policy and regulation information (the RBZ and the Ministry of
Finance)
References
1. Koop, G. (2006). Analysis of Financial Data. John Wiley
2. Montgomery, D. C., Peck, E. A., & Vining, G. G. (2021). Introduction to Linear Regression
Analysis. John Wiley & Sons.
3. Winston, W. L. (2004). Operations Research: Applications and Algorithms. Thomson
Brooks/Cole
