DATA6000 Capstone Industry Case Studies Report 1 Sample

DATA6000 Capstone Industry Case Studies Report 1

Your Task

Generate a unique business question that can be explored using available data sources and analytics methodologies mastered in the business analytics degrees.

Assessment Description

• An individual report of 1000-1500 words.

• Students are to investigate the application of one analytics method to an industry and document their findings as a report.

Assessment Instructions

The first part of any good project is a literature review. In approximately 1000-1500 words (excluding references) address the following sections that will assist you to outline a business industry problem that can be addressed through data analytics.

1. Industry Background:

Chose an Industry, e.g., healthcare, retail, education, finance, recreation, government, etc. and discuss three key business problems currently facing this industry.

2. Existing Analysis and Methodologies:

Investigate and evaluate existing analysis on the three business problems you have chosen and reflect on the data and analytics methodologies that have been employed this analysis.

3. Data Sources:

Evaluate the types of data sources available to analysts in this industry. Explore the available data sources you can access to address the three business problems you have identified and evaluate what type of descriptive and predictive analytics techniques could be used.

4. Selecting Business Problem:

Generate a unique business question for this industry based on one of the business problems. You will address this business problem in Assessment 3 (Project Report). For the business problem you select briefly summarise the:

1. The data source you will use.

2. Methodologies you will explore (brief).

3. The originality of your contribution (i.e. Why your is analysis unique given existing investigation and analysis in this space?).

5. Provide at least ten relevant, credible references to support your ideas and explanations.

Solution

1. Executive Summary

The point of discussion in this study is based on the identification of business problems in the retail industry through the application of descriptive, predictive and prescriptive analytics. Ineffective inventory management and lack of optimisation in the supply chain network in the retail industry has caused problem like overstocking and understocking, leading to degradation in profitability. Through the application of descriptive analytics (visualisation and summary statistics), factors affecting sales volume and customer churn in the retail industry can be addressed. On the other hand, through the application of predictive analytics (time-series forecasting and predictive modelling), fluctuation in retail sales can be addressed.

2. Industry Problem

2.1 Chosen Industry

Sales across the retail industry across the world are expected to increase significantly due to a rise in e-commerce sales. Global retail sales have reached more than 27 trillion USD in 2022 with a forecasted retail sales growth of 4.8% (Sabanoglu, 2022). In fact, large retail companies like Unilever, Tesco, Walmart, Amazon and more have experienced a Year-on-Year growth of 8,5% in 2022, which has increased by more than 5.2% compared to 2021 (Deloitte, 2023). This significant fluctuation in sales has caused challenges like inventory management and demand forecasting, leading to the occurrence of turmoil in the supply chain networks. It has been found that 51% of retail companies in the United States and the United Kingdom have struggled with demand and sales forecasting due to ineffective inventory management systems, leading to supply chain disruptions, logistic delays and sales drops (Smith, 2022c). In fact, inventory to sales in 2020 deteriorated to 1.09% in the retail trade industry, which has caused a loss in the form of the value of out-of-stock retail products of 569.7 billion USD (Smith, 2022b). In fact, poor inventory management systems have deteriorated the visibility of the supply chain network and caused logistic and shipping issues, leading to an inventory distortion cost of 677 million USD (Smith, 2022a). In addition to that, according to (Matuszelański and Kopczewska, 2022), high customer churn is another major problem in the retail industry that occurs due to logistic delays, deteriorated product quality and lack of customer support.

2.2 Identification of three business problems in the retail industry

Based on the analysis in 2.1, the identified business problems in the retail industry are stated below:

● Business Problem 1: Inefficient inventory management leads to stockouts or excess inventory, impacting sales and profitability.

● Business Problem 2: High customer churn rates impacting revenue and customer loyalty.

● Business Problem 3: Inaccurate sales forecasting leading to overstock or stockouts.

2.3 Reflection on the analytics methods and relevant data

Business analytics integrate descriptive, predictive and prescriptive analytics that can be utilised on customer and sales data of the retail industry to evaluate the adverse effect of ineffective inventory management on stock issues. In fact, through the evaluation of the customer data, assessment of factors affecting high customer churn in retail industry can be possible MBA assignment expert.

3. Data Sources and Potential Methodology

3.1 Data sources

Fluctuation in retail sales occurred due to logistic operations, fluctuation in customer demand and variation in shipping mode. For the evaluation of fluctuation in retail sales, data on shipping date, order date, shipping mode, logistic activity and many more have been collected from Kaggle (Kaggle, 2020). For the assessment of the impact of ineffective inventory management on supply chain operations and further on sales and demand imbalance, data sources like Statista, Deloitte and more have been considered. For the collection of customer data in the retail industry, data sources like Kaggle, IBISWorld and annual reports of large retail companies like Unilever, Tesco and more have been evaluated, which has helped in determining the factors affecting customer churn in the retail industry.

3.2 Evaluation of descriptive, predictive and prescriptive methodologies

Table 1: Descriptive, predictive and prescriptive methodologies

4. Business Problem

As per the viewpoint of Obadire, Boitshoko and Moyo (2022); Shabani et al. (2021), ineffective inventory management in the retail industry creates an imbalance in supply-demand conditions, leading to over-stocking and under-stocking issues in the retail industry. This creates a negative impact on the deterioration of customer satisfaction, leading to high customer churn in the retail industry.

Figure 1: Variation in customer Churn with satisfaction score in the retail industry
(Source: Developed in Power BI)

From Visualisation 1 (Descriptive analytics performed in Power BI) it has been found that customer churn in the retail industry is highest among dissatisfied customers. Lower levels of customer satisfaction occurred due to delayed delivery, stock issues and price fluctuation, occurred due to ineffective inventory management.

Figure 2: Average Customer Churn by Complaints
(Source: Developed in Power BI)

From Visualisation 2 (Descriptive analytics performed in Power BI) it has been identified the average customer retention rates are depicted along with the total number of complaints addressed. It indicates that when complaints grow, customer turnover rises as well, indicating that unhappy customers are inclined to discontinue their purchases.

Figure 3: Variation in Customer Churn by Category
(Source: Developed in Power BI)

From Visualisation 3 (Descriptive analytics performed in Power BI) the diversity in customer retention rates across various segments in the retail sector has been depicted. Fluctuation in customer churn in different retail sectors depicted the significance of product quality, technical support and customer services on customer satisfaction and further customer churn.

Figure 4: Variation in Sales by Category
(Source: Developed in Power BI)

As per the viewpoint of Chan et al. (2017), fluctuation in sales and demand conditions in the retail industry acted as a fundamental reason for ineffective inventory management, leading to logistic delays, stock issues and reduction in profitability. Figure 4 (developed in Power BI applying descriptive analytics methodology) shows that fluctuation in retail sales value (technology (0.83 million USD) and Office Supplies (0.7 million)), leading to fluctuation in supply-demand condition.

Figure 5: Descriptive Statistics of retail sales
(Source: Acquired from R Studio)

Figure 5 demonstrates the descriptive statistics of retail sales (performed in R Studio), indicating a large variation in sales value across the retail industry.

Figure 6: Fluctuation in sales over time
(Source: Developed in Power BI)

Significantly high fluctuation in retail sales volume has been observed in the time-series forecasting plot [Refer to Figure 6]. An increasing level of demand and low stock level (due to ineffective inventory management and demand forecasting) caused an enhancement in out-of-stock merchandise costs in the retail industry. it has been found that out-of-stock merchandise value in the retail grocery sector has increased by 568.7 billion USD in 2022 (Smith, 2022a). In fact, the supply chain costs of inventory distortion have reached 512 million USD in 2022 (Smith, 2022a). Therefore, in order to achieve the fluctuating demand and increase operational flexibility and profitability, retail companies need to optimise the inventory management system.

Figure 7: Time series plot of the retail sales over time
(Source: Developed using R studio)

Time series plot in Figure 7 indicates that the retail sales has fluctuated over time, depicting a fluctuation nature of retail sales due to market uncertainty and changing customer preferences.

Figure 8: ARIMA Model
(Source: Performed using R Studio)

The ARIMA (0,0,0) model with a non-zero mean for the ‘Sales’ time series indicates a stationary series without any autoregressive or moving average components. The estimated mean level is 230.7691 with a standard error of 6.3298. The variance of the series is 392693. Performance of the ARIMA model on training set demonstrates negligible bias (ME), on the other hand, the Root Mean Squared Error (RMSE) is relatively high at 626.6199, indicating moderate prediction error.

Figure 9: ARIMA Forecast of retail sales
(Source: Developed in R Studio)

The ARIMA forecast model indicates that retail sales will follow a pattern, indicating the stabilisation in the market.

Figure 10: Fluctuation in sales by shipping type
(Source: Developed in Power BI)

As per the viewpoint of Jafari and Paulraj (2021); Giannikas and McFarlane (2020), flexibility in terms of logistics and shipping mode contributed to the optimisation of supply chain networks, leading to effective inventory management. Sales volume through same-day delivery is significantly low (0.13 million USD), indicating the ineffectiveness of the retail companies in terms of optimised logistics and fast delivery options [Refer to Figure 7].

Figure 12: Output of the retail sales prediction model
(Source: Acquired from R Studio)

Predictive analytics technique (linear regression model) has been applied for the prediction of retail sales volume based on predictors like Order date, shipping mode and category. From the regression model, it has been found that the variable ‘Category’ is a significant predictor (with a p-value less than 0.05) for the prediction of sales volume. therefore, retail companies to optimise the inventory level for different product categories to fulfil fluctuating demand.

Figure 13: Logistic regression model for the prediction of customer churn
(Source: Developed in R Studio)

The results obtained from the logistic regression model indicates that customer churn in retail industry depends on factors like delivery speed (distance of warehouse to home), hours spend on shopping application, customer satisfaction, complaint resolution capability of the brand and cashbacks and discounts. Overall, the results indicate that, the positive coefficients (such as satisfaction score, Complaint) indicate increased odds of customer churn in retail, while the negative coefficients (such as Cashback Amount) suggest decreased odds.

5. Conclusion

Based on the above discussion it can be summarised that main business problem in retail sector is ineffective inventory management. Ineffective inventory management leads to inaccurate sales forecasting, leading to overstock and understock issue in the retail industry.

6. References

Chan, S.W., Tasmin, R., Nor Aziati, A.H., Rasi, R.Z., Ismail, F.B. and Yaw, L.P. (2017). Factors Influencing the Effectiveness of Inventory Management in Manufacturing SMEs. IOP Conference Series: Materials Science and Engineering, [online] 226(1), p.012024. doi: https://doi.org/10.1088/1757-899x/226/1/012024.

Deloitte (2023). Retail across the world | Deloitte Global. [online] www.deloitte.com. Available at: https://www.deloitte.com/global/en/Industries/consumer/analysis/retail-across-the-world.html [Accessed 29 Nov. 2023].

Giannikas, V. and McFarlane, D. (2020). Examining the value of flexible logistics offerings. European Journal of Operational Research, [online] 290(3), pp.968–981. doi: https://doi.org/10.1016/j.ejor.2020.08.056.

Jafari, H. and Paulraj, A. (2021). POSTPONEMENT and logistics flexibility in retailing: The moderating role of logistics integration and demand uncertainty. International Journal of Production Economics, [online] 243, p.108319. doi: https://doi.org/10.1016/j.ijpe.2021.108319.

Kaggle (2020). Superstore Sales Dataset. [online] www.kaggle.com. Available at: https://www.kaggle.com/datasets/rohitsahoo/sales-forecasting [Accessed 29 Nov. 2023].

Kaggle (2021). Ecommerce Customer Churn Analysis and Prediction. [online] Kaggle. Available at: https://www.kaggle.com/datasets/ankitverma2010/ecommerce-customer-churn-analysis-and-prediction [Accessed 29 Nov. 2023].

Matuszelański, K. and Kopczewska, K. (2022). Customer Churn in Retail E-Commerce Business: Spatial and Machine Learning Approach. Journal of Theoretical and Applied Electronic Commerce Research, [online] 17(1), pp.165–198. doi: https://doi.org/10.3390/jtaer17010009.

Obadire, A.M., Boitshoko, B.L. and Moyo, N.T. (2022). Analysis of the Impact of Inventory Management Practice on the Effectiveness of Retail Stores in South Africa. Global Journal of Management and Business Research, [online] 22(C5), pp.1–7. doi: https://doi.org/10.34257/GJMBRCVOL22IS5PG1.

Sabanoglu, T. (2022). Topic: Retail market worldwide. [online] Statista. Available at: https://www.statista.com/topics/5922/retail-market-worldwide/#topicOverview [Accessed 29 Nov. 2023].

Shabani, A., Maroti, G., de Leeuw, S. and Dullaert, W. (2021). Inventory record inaccuracy and store-level performance. International Journal of Production Economics, [online] 235, p.108111. doi: https://doi.org/10.1016/j.ijpe.2021.108111.

Smith, P. (2022a). Inventory distortion costs breakdown in retail industry 2020. [online] Statista. Available at: https://www.statista.com/statistics/1199064/inventory-distortion-costs-breakdown-in-retail-industry/ [Accessed 29 Nov. 2023].

Smith, P. (2022b). Topic: Retail supply chain. [online] Statista. Available at: https://www.statista.com/topics/7638/retail-supply-chain/#topicOverview [Accessed 29 Nov. 2023].

Smith, P. (2022c). US: retail inventory management solutions 2020. [online] Statista. Available at: https://www.statista.com/statistics/1224037/retail-inventory-management-solutions-united-states/#:~:text=Retail%20inventory%20management%20solutions%20in%20the%20U.S.%202020&text=According%20to%20a%202020%20poll [Accessed 29 Nov. 2023].