lOMoARcPSD|15788763 Visual presentation - OB assignment Organizational Behavior (Sukkur Institute of Business Administration) Scan to open on Studocu Studocu is not sponsored or endorsed by any college or university Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 DATA DRIVEN DECISIONS FOR BUSINESS Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 TABLE OF CONTENTS Introduction and project plan..........................................................................................................................................1 Data quality issues and remedies....................................................................................................................................1 Data analysis and commentary.......................................................................................................................................3 Issue 2 Solution:.........................................................................................................................................................6 Issue 1 Solution:.........................................................................................................................................................8 Data charting and commentary.......................................................................................................................................9 Issue 3 Solution:.......................................................................................................................................................10 Conclusions and recommendations...............................................................................................................................11 References.....................................................................................................................................................................12 Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 INTRODUCTION AND PROJECT PLAN This section will present a comprehensive outline of the research project and rationalize the proposed approach for its dissemination to the Corporate Strategy Manager at Café on the Sea (COTS). The present study aims to elucidate the potential of data analytics in enhancing the business performance of COTS's coffee shops by referring to a pertinent data analytics framework. The aim of this report is to conduct an analysis of the present business performance of COTS's coffee shops and offer insights and recommendations for strategic decision-making. The utilization of data analytics can provide significant insights to facilitate evidence-based decisionmaking and enhance performance. Data quality issues were observed in the dataset, including the presence of missing values and inconsistent entries. We have proposed the utilization of data cleansing techniques through the utilization of Excel's tools to tackle these issues. The study involved conducting targeted analyses aimed at identifying underperforming products and selecting the optimal coffee shop for expansion. The impact of a home delivery service on sales performance was also evaluated. The project will be executed in adherence to a data analytics framework, thereby guaranteeing a thorough and dependable analysis. The utilization of data analytics possesses the capability to enhance business performance through the revelation of valuable insights, recognition of prospects, and augmentation of customer experiences. Our report will provide comprehensive insights and practical suggestions to the Corporate Strategy Manager, enabling them to make well-informed choices and enhance the expansion and profitability of COTS's coffee shops. DATA QUALITY ISSUES AND REMEDIES When gathering, integrating, and cleansing data, analysts frequently face a few common problems. Because of these obstacles, the data may not be as high-quality, reliable, or helpful as it could be for analysis. Common problems are listed below: 1. Data Availability and Accessibility: Data analysts may face difficulties in obtaining access to relevant data sources. Some data may be proprietary or confidential, making it challenging to acquire. Additionally, data may be scattered across multiple systems or departments, requiring coordination and cooperation to gather the necessary data (Singh & Dwivedi, 2020) 2. Data Quality and Accuracy: Data can suffer from quality issues such as missing values, inconsistencies, duplication, and outliers. Incomplete or inaccurate data can lead to biased Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 3. 4. 5. 6. 7. 8. or incorrect analysis. Data analysts must identify and address these issues through data cleaning techniques to ensure the reliability of their analysis (Singh & Dwivedi, 2020). Data Integration and Data Silos: Integrating data from different sources can be complex, especially when dealing with incompatible formats, data structures, or naming conventions. Data silos, where data is stored in isolated systems or departments, can hinder data integration efforts. Data analysts need to consolidate and transform data into a unified format to enable meaningful analysis (Jagadish et al., 2014). Data Relevance and Context: Data analysts must ensure that the collected data is relevant to the analysis objectives. They need to understand the context of the data and its limitations. Without considering the relevance and context, the analysis may produce misleading or incomplete insights (Jagadish et al., 2014).. Data Privacy and Security: Data analysts must adhere to data privacy regulations and ensure the protection of sensitive information. Anonymization or pseudonymization techniques may be required to safeguard personal or confidential data. Data security measures must also be in place to prevent unauthorized access or data breaches. Data Bias and Preprocessing Biases: Bias can be inherent in the data collection process or introduced during data preprocessing. For example, sampling bias may occur if the data collection process is skewed towards specific demographics or locations. Preprocessing steps such as data filtering, transformation, or feature selection can also introduce bias if not carefully managed. Data Volume and Scalability: Handling large volumes of data can pose challenges in terms of storage, processing power, and computational resources. Data analysts may need to employ techniques such as data sampling, aggregation, or parallel processing to manage and analyze large datasets efficiently. Data Governance and Documentation: Establishing proper data governance practices is crucial to maintain data quality, traceability, and transparency. Data analysts should document the data collection, integration, and cleaning processes to ensure reproducibility and facilitate collaboration with other team members or stakeholders (Singh & Dwivedi, 2020. Data analysts apply a wide variety of approaches and tools, including data cleansing algorithms, data integration frameworks, statistical methods, and data governance frameworks, to address these difficulties. To further evaluate data accuracy, address specific data concerns, and guarantee the data's relevance and trustworthiness for analysis, they work closely with subject experts and data stakeholders. The quality and usefulness of the data, as well as the reliability and significance of the insights it yields, can be enhanced by data analysts' being cognizant of these overarching problems and employing best practices in data collection, integration, and cleansing. Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 Based on the provided dataset, here are the data problems that are identified: 1. Missing values: In the dataset, some entries have missing values. For example, in the row "Southampton 2020 2 Hot drinks - £0," the sales volume is missing. This can cause issues in data analysis and calculations. 2. Typos and inconsistent values: There are variations in the naming conventions used for product groups, such as "Cold drinks" and "Colddrinks," "Pastry" and "Pazztry," and "Sandwiches" and "Sandwich." This inconsistency can lead to confusion and inaccuracies in data analysis. To address this, a data cleansing process can be implemented to standardize the naming conventions and ensure consistency throughout the dataset. 3. Incorrect column headers: The column header "Product category" is misspelled as "Product category" This inconsistency can lead to confusion and affect data interpretation. 4. There is an inconsistency in the year entry, where "2032" is used instead of "2023," Here are the identified data problems and possible solutions using Excel's data validation and other tools: 1. Inconsistent product category names: In the dataset, the product category names have variations like "Coffee," "Hot drinks," "Cold drinks," etc. To address this, you can create a list of valid product categories in a separate sheet or column and use Excel's data validation feature to create a drop-down list for the product category column. This ensures consistent and accurate category entries. 2. Missing sales values: In some instances, the sales value is missing or represented as "-". To address this, you can use Excel's data validation to ensure that the sales value column only accepts numeric values. You can set up a rule to flag or highlight any invalid or missing values, allowing you to manually input or correct them. 3. Misspelled product category: There is a misspelled category name "Pazztry" in one of the entries. To address this, you can use Excel's Find and Replace feature to search for and correct the misspelled category name. Alternatively, you can create a lookup table with correct category names and use Excel's VLOOKUP or INDEX-MATCH functions to replace the incorrect entries. 4. By following these steps, we can quickly correct the inconsistency in the year entry throughout the dataset. Make sure to double-check the entries after replacing to ensure all the incorrect years have been successfully updated to "2023." Select the column containing the year entries that need to be corrected. Go to the "Home" tab in Excel. Click on the "Replace" button in the "Editing" group, or press Ctrl + H on your keyboard. The Find and Replace dialog box will appear. In the "Find what" field, enter "2032" (the incorrect year). In the "Replace with" field, enter "2023" (the correct year). Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 Click on the "Replace All" button to replace all instances of "2032" with "2023" in the selected column (Devi & Kalia, 2015). DATA ANALYSIS AND COMMENTARY Table A Sales volume and value by month, by year and across the 3 years period Year and Months Sum of Sales Value Sum of Sales Volume 58742.25 18629.5 1 4022.25 1229.5 2 3263.5 1330.5 3 4877.75 1530 4 5456.5 1735.5 5 4869.75 1513 6 5103.75 1591.5 7 5772.5 1755 8 5846.25 1819.5 9 4838 1508 10 4915.25 1522 11 4651.25 1480 12 5125.5 1615 62502.25 19677.5 1 4219.25 1307 2 4486.25 1395.5 3 5015.25 1541 4 6127 1914 5 4355.25 1459 6 5487.75 1723.5 7 5717 1766 8 6246.5 1935 9 5180.25 1588 10 5373 1659.5 11 5333 1671.5 12 4961.75 1717.5 68967.11 21609.192 4189.75 1300 2020 2021 2022 1 Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 2 4717.25 1456 3 5293.75 1629.5 4 6398.75 2013.5 5 5313.25 1675 6 5663.194 1804.456 7 6780.642 2119.458 8 7746.294 2408.606 9 5940.85 1881.81 10 5936.346 1882.732 11 6229.862 1936.802 12 4757.172 1501.328 2023 1180.5 360 12 1180.5 360 191392.11 60276.192 Grand Total Table B Benchmark comparisons of product group’s performance covering sales volume and value by quarter, by year and across the 3 years period Sum of Sales Volume Row Labels Column Labels 1-3 4-6 7-9 10-12 Grand Total 1181.5 1336.992 1477.098 1360.4 5355.99 2020 376 446 475 421.5 1718.5 2021 400.5 390 510 429.5 1730 2022 405 500.992 492.098 474.4 1872.49 35 35 Cakes 2023 Coffee 3923.5 4687.2 5071.976 4580.016 18262.692 2020 1288.5 1525.5 1567.5 1338 5719.5 2021 1272.5 1605.5 1591 1576.5 6045.5 2022 1362.5 1556.2 1913.476 1545.516 6377.692 120 120 2032 Cold drinks 2384 2946.532 3215.848 3001.212 11547.592 2020 721.5 893 967.5 903 3485 2021 819 915 1079.5 983.5 3797 Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 2022 843.5 1138.532 1168.848 2023 Colddrinks 171 105 2020 91.5 105 2021 79.5 4202.592 63 63 187 463 196.5 79.5 2022 Hot drinks 1051.712 187 187 1833.5 2328.512 2441.492 2268.408 8871.912 2020 562 722 767 687 2738 2021 677.5 764.5 787 712 2941 2022 594 842.012 887.492 820.408 3143.912 49 49 2023 Kakes 45 2021 45 2022 49.5 94.5 45 49.5 49.5 Pastry 2402 2992.56 3318.368 3173.934 11886.862 2020 812.5 847.5 993.5 1001 3654.5 2021 676 1080 993 1054.5 3803.5 2022 913.5 1065.06 1331.868 1118.434 4428.862 Pazztry 59 89 72 220 2021 59 2022 59 89 89 2023 Sandwich 39 2021 19 2022 20 Sandwiches 72 72 34.5 73.5 19 34.5 54.5 764.5 859.66 1020.092 855.892 3500.144 2020 238 301 312 266.5 1117.5 2021 259.5 277.5 328.5 292.5 1158 2022 267 281.16 379.592 275.892 1203.644 21 21 2023 Grand Total 12719 15429.45 6 16781.374 15346.362 Downloaded by saad tanveer (saadtanveer112@gmail.com) 60276.192 lOMoARcPSD|15788763 ISSUE 2 SOLUTION: Products with the worst sales performance which are the candidates to be removed from the shops’ menu. Producct Category Sum of Sales Value Sum of Sales Volume Cakes 26779.95 5355.99 Coffee 71970.768 18262.692 Cold drinks 27953.98 11547.592 Colddrinks 1157.5 463 Hot drinks 17743.824 8871.912 Kakes 472.5 94.5 Pastry 23431.724 11886.862 Pazztry 440 220 Sandwich 441 73.5 Sandwiches 21000.864 3500.144 Grand Total 191392.11 60276.192 products with the worst sales performance which are the candidates to be removed from the shops’ menu 80000 70000 60000 50000 40000 Sum of Sales Value Sum of Sales Volume 30000 20000 10000 0 The sales data provided for each category can be analysed to see which products performed the worst. The data allows us to examine the "Sum of Sales Volume" column and identify the lowvolume products that could be dropped from the menu. The numbers show that "Colddrinks," "Kakes," "Pazztry," and "Sandwich" sell at much lower rates than the rest of the store's offerings. The poor sales performance of these items makes them possible candidates for removal from the menu. Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 We can safely disregard the "Colddrinks" entry because it looks to be a duplicate category. If the Procurement Manager gets rid of these underperforming items, they can streamline the menu, cut down on overall ingredient costs, and maybe boost profits. Sum of Sales Volume Sum of Sales Value Row Labels 2020 2021 2022 Blackpool 8315 8753 1-3 1844 4-6 Total Sum Sales Value of 2020 2021 2022 10443.692 26564 27831 33385.36 27511.692 87780.36 2014 1890 5883 6428 6191 5748 18502 2077 2189 2485.456 6587 6781 7912.694 6751.456 21280.694 7-9 2324 2320 3194.874 7486 7462 10165.036 7838.874 25113.036 10-12 2070 2230 2873.362 6608 7160 9116.63 7173.362 22884.63 6076.5 6490.5 6859.5 18483.7 5 20298.75 21876.75 19426.5 60659.25 1-3 1371 1231.5 1453.5 3409.5 4101.75 4655.25 4056 12166.5 4-6 1659 1735.5 1762.5 5290.5 5439 5581.5 5157 16311 7-9 1597.5 1818 1944 5204.25 5865.75 6204.75 5359.5 17274.75 1449 1705.5 1699.5 4579.5 4892.25 5435.25 4854 14907 216 536 684 1609.5 773 2419.5 46 92 463 1463.5 Portsmouth 10-12 Southam 1-3 202 3 Total Sum of Sales Volume 21 46 4-6 1463.5 170 73 21 4238 4218 3770 339 1-3 875 952 4-6 1104 7-9 10-12 Southampton Grand Total 126 92 463 10-12 2023 592 146 126 264 864 13694.5 13688.5 12095.5 1054.5 12565 40533 1042 2871 3099 3354.5 2869 9324.5 1172 782 3552.5 3750 2417.5 3058 9720 1161 1151 1271 3766.5 3816 4098 3583 11680.5 1098 943 675 339 3504.5 3023.5 2225.5 1054.5 3055 9808 18629.5 19677.5 21609.192 360 58742.2 5 62502.25 68967.11 1180.5 60276.192 191392.11 Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 Table C Benchmark comparisons of sales volume and value between coffee shops by quarter, by year and across the 3 years period ISSUE 1 SOLUTION: Three coffee shops to identify the best shop to invest in expanding its floor area. Coffee Shop Sum of Sales Value Sum of Sales Volume Blackpool 87780.36 27511.692 Portsmouth 60659.25 19426.5 Southampton 40533 12565 Grand Total 188972.61 59503.192 Three coffee shops to identify the best shop to invest in expanding its floor area. Southampton Sum of Sales Value Sum of Sales Volume Portsmouth Blackpool 0 10000 20000 30000 40000 50000 60000 70000 80000 90000100000 To assess the performance and potential for expansion, we can consider both sales value and sales volume. Sales Value Analysis: Blackpool: £87,780.36 Portsmouth: £60,659.25 Southampton: £40,533 Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 Based on sales value alone, Blackpool has the highest revenue, indicating a stronger financial performance compared to the other coffee shops. Sales Volume Analysis: 1. Blackpool: 27,511.692 2. Portsmouth: 19,426.5 3. Southampton: 12,565 Blackpool also performs better than the other coffee shops in terms of sales volume, suggesting a higher frequency of client transactions. Blackpool is the most promising coffee shop for growth, both financially and in terms of potential customer base. When compared to Portsmouth and Southampton, it outperforms both in terms of sales revenue and client base. Because of its success and high demand, the Corporate Strategy Manager should think about increasing the coffee shop's footprint in Blackpool. DATA CHARTING AND COMMENTARY Comparison of sales value trends across coffee shops over time 40000 35000 30000 25000 Total 20000 15000 10000 5000 0 Chart A Comparison of sales value trends across coffee shops over time Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 Product category performance comparisons between coffee shops 9000 Cakes Coffee Cold drinks Colddrinks Hot drinks Kakes Pastry Pazztry Sandwich Sandwiches 8000 7000 6000 5000 4000 3000 2000 1000 0 Blackpool Portsmouth Southam Southampton Chart B Product category performance comparisons between coffee shops ISSUE 3 SOLUTION: The home delivery service offered in Blackpool have a positive impact on the sales performance of the shop? Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 Impact of the home-delivery service offered in the Blackpool area, and in comparison with the other two cities. Southampton; 21.18% Southam; 1.26% Blackpool; 45.86% Blackpool Portsmouth Southam Southampton Portsmouth; 31.69% Chart C Impact of the home-delivery service offered in the Blackpool area, and in comparison with the other two cities. Given the available data, it seems reasonable to conclude that the home delivery service has contributed to the growth of the Blackpool store's revenue. When compared to the other locations in the chain, Blackpool's sales (£87,780.36) far outpace those of Portsmouth (£60,659.25), Southam (£2,419.50), and Southampton (£40,533.00). Since Blackpool's sales value is much greater than the sales values of other shops in the chain, this may indicate that the Blackpool store's sales performance has improved as a result of the launch of the home delivery service. In light of this information, it seems reasonable to infer that the home delivery service introduced in the Blackpool store was a significant factor in its better sales performance compared to the other stores in the company. To prove a definitive causal relationship between the home delivery service and the increased sales, a more extensive analysis is needed, including full sales data and comparison before and after the introduction of the service. CONCLUSIONS AND RECOMMENDATIONS In conclusion, the data provided by the customer allowed for insightful conclusions to be drawn about the sales performance of product categories and coffee shops. We fixed the data issues with Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 data cleansing methods, making the data set reliable and consistent. More educated choices about menu optimization, cost reduction, and possible profit rise might be made after underperforming products were exposed. We also found that the Blackpool coffee shop had the most potential for growth by comparing its sales volume and value to those of other coffee shops. Last but not least, the Blackpool store's sales increased after it began offering home delivery. Based on the findings, it is recommended to take the following actions: 1. Implement data cleansing techniques to address missing values, typos, inconsistent values, and incorrect column headers in the dataset. This will ensure the accuracy and reliability of future analyses. 2. Consider removing low-performing products, such as "Colddrinks," "Kakes," "Pazztry," and "Sandwich," from the menu. This will streamline the menu, reduce ingredient costs, and potentially increase profitability. 3. Focus on expanding the floor area of the Blackpool coffee shop, as it has shown the highest sales value and volume among the analyzed coffee shops. This expansion will accommodate the growing customer base and capitalize on the shop's strong performance. 4. Continue offering the home delivery service in the Blackpool shop, as it has shown a positive impact on sales performance. Monitor the service's effectiveness closely and make further improvements based on customer feedback and market trends to sustain its success. Through the implementation of these suggestions, the coffee chain can effectively optimize its menu offerings, strategically allocate resources towards shop expansion initiatives, and leverage successful services to bolster sales and improve overall business performance. Downloaded by saad tanveer (saadtanveer112@gmail.com) lOMoARcPSD|15788763 REFERENCES Singh, S. K., & Dwivedi, R. K. (2020). Data Mining: Dirty Data and Data Cleaning. Available at SSRN: https://ssrn.com/abstract=3610772 or http://dx.doi.org/10.2139/ssrn.3610772 Jagadish, H. V., Gehrke, J., Labrinidis, A., Papakonstantinou, Y., Patel, J. M., Ramakrishnan, R., & Shahabi, C. (2014). Big data and its technical challenges. Communications of the ACM, 57(7), 86-94. doi:10.1145/2611567 Devi, S., & Kalia, A. (2015). Study of Data Cleaning and Comparison of Data Cleaning Tools. International Journal of Computer Science and Mobile Computing, 4(3), 360-370. Downloaded by saad tanveer (saadtanveer112@gmail.com)