0% found this document useful (0 votes)
60 views16 pages

Assignment

Tesco utilizes cloud-based infrastructure and centralized data lakes for efficient data warehousing and decision-making, ensuring compliance with data governance policies like GDPR. The sales data from 2020 to 2023 shows a positive linear trend with seasonal fluctuations, indicating consistent demand and market response. External factors such as Brexit, taxation changes, and consumer preferences significantly impact Tesco's sales performance and future forecasts.

Uploaded by

Ranjita Gautam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
60 views16 pages

Assignment

Tesco utilizes cloud-based infrastructure and centralized data lakes for efficient data warehousing and decision-making, ensuring compliance with data governance policies like GDPR. The sales data from 2020 to 2023 shows a positive linear trend with seasonal fluctuations, indicating consistent demand and market response. External factors such as Brexit, taxation changes, and consumer preferences significantly impact Tesco's sales performance and future forecasts.

Uploaded by

Ranjita Gautam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

1.

Evaluation of Tesco’s Policies and Practices of Data Warehousing and Storage

Tesco, as one of the UK’s largest retailers, handles large volumes of data from various
sources such as in-store purchases, loyalty programs, online sales, supply chains, and
customer service.

The policies and practices adopted by Tesco for data warehousing and storage and its role in
decision making

a. Cloud-Based Infrastructure

Tesco has adopted cloud computing to manage its large data resources. By leveraging
Microsoft Azure platform,

Azure provides the scalability and flexibility required to process bulk data of sales, supply
chain, operations and customer. By leveraging real time analytics tools such as Databricks,
Data lake services and Azure Synapse, Tesco makes decisions by using dashboards and
reports instantly. Cloud computing solutions help Azure to make accurate and timely
decisions.

b. Centralized Data Lakes

Tesco stores both structured and unstructured data using a central data lake. The approach
facilitates data integration from several sources such as sales transaction, supply chain
metric, comprehensive analysis and customer interactions.

Tesco has also transformed its data storage practices from traditional data warehouse to
Hadoop- based data lake framework. This shift allows Tesco to access data and derive its
insights regardless of location, facilitating an efficient and more integrated environment.

c. Data Governance and Compliance

Tesco complies with data governance policies to ensure data security, and compliance with
regulations like the General Data Protection Regulation (GDPR). These policies include data
encryption, access controls, and timely audits to protect sensitive information and maintain
customer trust.

Tesco’s stringent data governance policies—including access controls, encryption and


compliance with GDPR. By complying with GDPR, Tesco gains customer trust and protects
itself from reputational damage, allowing the business to operate confidently in European
and global markets. Given the Tesco complies to GDPR, stakeholders trust that the numbers
in BI dashboards are secure, unfabricated, and reliable, making them comfortable in using
such data for strategy or investment decisions.

2. Past five years (2020 – 2024) Data of Tesco


Sales Movin
(in g De-
billion Averag (Sales/ Season season Foreca
Year Q Period £) e (4) CMA CMA) ality ality FTrend sting
2020 Q1 1 11.8
Q2 2 12.4
Q3 3 12.9
12.637 1.0497
Q4 4 13.2 12.575 5 01789
12.762 0.9685 1.0142 12.127 9.7966 9.9359
2021 Q1 5 12.3 12.7 5 03937 25518 48031 08039 69864
12.887 1.0058 12.719 9.8248 9.9646
Q2 6 12.9 12.825 5 47953 06472 48268 11824
13.012 1.0347 13.212 9.8530 9.9932
Q3 7 13.4 12.95 5 49035 05172 88497 53785
13.237 1.0478 13.507 9.8813 10.021
Q4 8 13.7 13.075 5 01147 84392 28725 89575
1.0149 0.2537 9.9095 2.5143
2022 Q1 9 13.6 13.4 13.575 25373 313433 53.6 68954 68242
56.358 9.9378 2.5215
Q2 10 14.3 13.75 13.925 1.04 82353 09183 33673
1.0496 58.329 9.9660 2.5286
Q3 11 14.8 14.1 14.275 4539 41176 49411 99104
14.512 1.0449 59.511 9.9942 2.5358
Q4 12 15.1 14.45 5 82699 76471 8964 64535
0.9674 0.7494 18.813 10.022 7.5115
2023 Q1 13 14.1 14.575 14.625 099485 695829 3052 52987 8128
1.0017 19.613 10.050 7.5327
Q2 14 14.7 14.675 14.725 03578 87138 7701 46472
14.837 1.0287 20.281 10.079 7.5539
Q3 15 15.2 14.775 5 64805 00986 01033 11665
1.0469 20.814 10.107 7.5750
Q4 16 15.6 14.9 15.05 79866 72065 25055 76857
2024 Q1 17 15.3 15.2
Q2 18
Q3 19
Q4 20
2025 Q1 21
Q2 22
FTrend=
9.6554+
(0.028×
Q3 23 period)
Q4 24

3. Analysis of 3 Key Trends and Patterns of Tesco’s Sales Data from 2020-2025
Based on the calculation performed above, we have identified the following trends and
patterns.
● Positive Linear trend.

The Sales figure of Teco from 2020 to 2025 show a steady increment from 11.8 billion in
2020 Q1 to 15.6 billion in 2023 Q4. Similarly, the F Trend and Deseasonalized value also
provided evidence of the positive trend.

○ The FTrend (Forecasted Trend) formula =9.6554 + (0.028 × Period) increases


steadily in every quarter.

○ The Deseasonalized values also rise over time, confirming growth after
removing seasonal effects.

The overall trend depicts that Tesco is experiencing a positive linear trend, likely due to
increased market demand, improved performance, or product expansion.

● Clear Seasonal Patterns Across Quarters

The analysis of Seasonal patterns shows that a few seasons have an uptrending pattern and
the remaining few have a low trending pattern.

○ The Sales/CMA ratio shows a fluctuating and repeating pattern which


indicates a seasonal component in Tesco's sales.
○ Q1 typically has lower ratios (e.g., 0.968 in 2021 Q1, 0.967 in 2023 Q1),
suggesting lower sales volume on the first quarter.
○ Q3 and Q4 consistently have greater ratios (~1.04–1.05), indicating higher
seasonal performance in these quarters.
The Seasonality Index supports this trend, with values like 1.014 for Q1 and 1.034 for Q3,
confirming the uptrending sales pattern.In overall, Sales performance is seasonally
influenced, with Q3 and Q4 outperforming Q1 and Q2 consistently.

● Slowing Growth or Plateau

The Forecasted values (based on trend × seasonality) rise until a point but start to become
flat:

● 2022 Q4 Forecast: ~2.53

● 2023 Q4 Forecast: ~7.57

But despite rising FTrend values, the Forecasting values rise slowly, indicating possible
market stabilization.Also, Q1 2024 doesn't show a significant rise from previous quarters.

In overall, the forecasted sales trend indicates sluggish growth beyond 2023, suggesting that
Tesco may be entering a maturity phase with limited room for market expansion.

4. Four-period moving average (MA) and centred moving average (CMA) and its
effectiveness in forecasting.
● Moving Average
The moving average is a method used to smoothen short-term fluctuations in sales
data and highlight the trend beneath. It is effective in forecasting the future trend by
providing the following advantages.
○ Useful for identifying general trends over the period of time.

○ Helps reduce fluctuations from irregular variations.

○ Suitable for short-term forecasting when data does not depict strong
seasonality.
○ However, it can lag behind incase of highly seasonal data hence could be less
effective in highly seasonal patterns.

The calculated Moving Average for 2021 Q1 was 12.7, and for 2023 Q1, it was 14.575. This
shows how the moving average smooths out fluctuations over time and helps identify the
overall trend, showing insights into whether the sales are increasing or decreasing.

● Centered Moving Average (CMA):


CMA is calculated by taking the average of two consecutive moving averages. It
centers the values to align with the actual time periods. It is effective in forecasting
the future trend by providing the following insights:
○ Helps in identifying and removing seasonality from time series data.

○ Facilities break down of sales data into trend and seasonal components.

○ Provides a more accurate basis for forecasting when seasonality is present.

○ Supports the calculation of seasonal indices, which are used to adjust


forecasts for seasonal effects.

For 2021 Q1, the calculated CMA was 12.7625, and for 2023 Q1, it was 14.625. The CMA
smoothens the fluctuations from the sales data, aligning the data better with the actual
periods and showing a clearer picture of the sales trend. It also provides the identification of
seasonal patterns.

5. Evaluation of descriptive, diagnostic, predictive, and prescriptive frameworks and


their relevance to business strategy.
● Descriptive Analytics

Descriptive analytics summarizes historical data to understand the scenario.

When we apply Descriptive analysis to summarize Tesco’s history data, it shows that:

● Moving Average (MA) and Centered Moving Average (CMA) smoothed out
fluctuations to reveal the underlying trend.
From the analysis of Moving Average and Centered Moving Average, we can describe
Tesco’s sales performance over time—identifying its growth, dips, or seasonal patterns.

Relevance to Business Strategy

● Allows Tesco to review past sales performance.

● Helps decison making team to understand consumer demand patterns over


different quarters.

● Supports performance tracking of strategic initiatives like brand strategies, seasonal


promotions or pricing changes.

Diagnostic Analytics

Diagnostic analytics provides answer to why questions related to scenario—digging into


relationships and patterns.

Applying Diagnostic Analysis on Tesco’s Sales Data:

● The calculation of (Sales/CMA) and Seasonality Index helps to calculate the


magnitude and cause of seasonal effects.

● Comparing quarters and analyzing deviations allows decision makers to identify


which periods had exceptional or poor performance, possibly due to external
factors (e.g., pandemic, holidays, weather, etc.).

Relevance to Business Strategy

● Helps Tesco team determine why sales increaed or decreased in certain quarters.

● Enables the company to align promotional campaigns, inventory levels, or staffing


needs to demand patterns.
● Informs whether external factors (economic,social, competitor actions) are
influencing sales performance.

Predictive Analytics
Predictive analytics uses historical data to forecast future outcomes.

Applying Predictive Analysis to Tesco analysis:

● Calculation of linear regression using slope and intercept (FTrend) to forecast future
sales.

● Forecast of upcoming trends by combining trend line with seasonal indices.

Relevance To Business Strategy

● Provides forecasted sales volumes, helping Tesco to plan demand, inventory


level , and supply chain.

● Allows proactive budgeting and staffing based on forecasted demand.

● Supports Tesco in strategic decision-making (e.g., launching new products,


store expansions) based on expected growth.

Prescriptive Analytics
Prescriptive analytics recommends actions to take based on data.

Applying Prescriptive Analytics on Tesco’s data


While we haven’t explicitly worked on a prescriptive model, the analysis that we made so
far sets the foundation for Prescriptive Analytics.

● The sales forecasts enables Tesco to determine how much inventory to maintain or
which locations to prioritize.

● If integrated with cost, capacity or location Tesco could optimize promotions,


reduce wastage, or maximize profit.
Relevance To Business Strategy

● Prescriptive insights guide resource allocation (e.g., warehousing, inventory,


logistics).

● Helps align marketing and sales strategies with peak demand periods.

● Could assist decison makers in automated decision systems, like dynamic pricing or
just-in-time inventory.

6. Interpretation of Sales Trend and External Factors that have impact on Tesco’s sales.
Based on the data for Tesco from 2020 to 2023, a positive trend in sales is observed, with
incremental growth in most quarters. The sales figures increased gradually from 2020
through 2023, reflecting increasing business performance. For example:

○ 2020 sales started at £11.8 billion in Q1 and ended at £13.2 billion in Q4.

○ By 2023, Sales for Q4 reached £15.6 billion.

○ This steady rise in sales suggests consistent demand for Tesco's products and

a positive market response.

○ Using the trend formula FTrend=9.6554+(0.028×period)FTrend = 9.6554 +

(0.028 \times period)FTrend=9.6554+(0.028×period), we anticipate

continuing upward sales growth through 2025. This indicates that the

company an expect for further growth, reducing disruptions.

The sales trend over the past five years shows a steady increase in sales, with some
seasonal fluctuations observed in each quarter. The periodic rise, especially in Q3 and Q4,
may suggest stronger seasonal performance, potentially due to seather, holiday seasons or
other environmental events driving demand.
External Factors Affecting Sales

1. Brexit has had a significant impact on the UK market, creating disruptions related to
trade, labor force availability, and supply chain. Such political changes can affect
Tesco's costs, product availability, and ultimately sales figures.

2. Changes in taxation policies or regulations can also affect pricing strategies, supply
chains, and ultimately sales performance of Tesco . Any new tariffs, tax reform and
import/export restrictions could directly influence the company's bottom line.

3. The Covid-19 pandemic had a significant effect on Tesco's sales, particularly during
the lockdown when grocery demand increased due to panic buying, but in-person
shopping was limited. Post-pandemic recovery may have shifted consumer behavior
(e.g., preference for online shopping or local sourcing) can continue to impact how
Tesco operates and its sales.

4. Changing consumer preferences, such as increasing demand for sustainable


products,, mindful shopping or plant-based food items, can also change demand,
influencing revenue growth.

7. Applying predictive analytics techniques to forecast sales for 2025, discussing the
accuracy and reliability of predictions.

a. Linear Regression (Trend Line Forecasting)

Since we have already calculated the Trend (using slope and intercept) as part of the sales
analysis so far. This trend can be extended to predict future sales volume. The formula for
the trend is:

FTrend=a+b×PeriodFTrend = a + b \times \text{Period}FTrend=a+b×Period

Where:
● aaa is the intercept (9.6554 in your analysis).

● bbb is the slope (0.02824022868 in your analysis).

● Period corresponds to the future time point of prediction (e.g., 2025).

Once the trend is established, seasonality should be adjusted in account of periodic


fluctuations due to seasons (as identified using the Seasonality Index in our analysis).

To adjust for seasonality:

Forecasted Sales=FTrend×Seasonality Index\text{Forecasted Sales} = FTrend \times \


text{Seasonality Index}Forecasted Sales=FTrend×Seasonality Index

Another method for predicting future sales is by extending the Moving Average (MA),
especially if it depicts any significant shifts. We can forecast future sales using a rolling
average that smooths out fluctuations. However, this may not account for future trend as
well as the linear regression approach.

Forecasting Sales for 2025

Given the available data (through 2024), let’s forecast sales for the first quarter of 2025 (Q1
2025) as an example. Here’s a breakdown of the steps:

1. Forecasting Trend (FTrend):


Using the linear regression formula with a slope of 0.02824022868 and an intercept
of 9.655406896, forecast for Q1 2025 (Period 21):

FTrend=9.6554+(0.02824022868×21)\text{FTrend} = 9.6554 + (0.02824022868 \


times 21)FTrend=9.6554+(0.02824022868×21)
2. Adjusting for Seasonality:
You can adjust the trend forecast by applying the Seasonality Index for Q1 (which
you can calculate or assume based on historical data). For simplicity, let's assume the
seasonality for Q1 is 1.01 (this is hypothetical and should be derived from past data).

Forecasted Sales=FTrend×Seasonality Index\text{Forecasted Sales} = \text{FTrend} \


times \text{Seasonality Index}Forecasted Sales=FTrend×Seasonality Index

8. Recommendations to Tesco to enhance business performance and secure a competitive


advantage.

Capitalize Seasonal Sales: Tesco should continue to capitalize on the observed seasonal
sales peaks, particularly in Q3 and Q4, by optimizing inventory management and increasing
stock during high-demand periods (e.g., festive seasons, back-to-college shopping, and
holidays). Additionally, employing dynamic pricing strategies during these times can help
maximize revenue.

● Actionable Steps:

○ Use predictive analytics to forecast seasonal sales more accurately based on


historical trends (e.g., leveraging seasonality indexes like those calculated in
the data).

○ Implement real-time inventory tracking and data-driven inventory stock


processes to prevent stockouts and minimize overstock.

○ Optimize supply chain partnerships to ensure timely and efficient delivery of


popular products during peak times.

Enhance Online Presence: With the rise of online shopping and shifting consumer behavior
after Covid-19, Tesco should invest further in its e-commerce platform to enhance the
customer experience and improve online sales.

● Actionable Steps:

○ introducing features like personalized shopping, AI-powered personalizations


and recommendations to increase customer engagement and conversion
rates.

○ Implement a click-and-collect service for customers who prefer shopping


online but like to pick up their purchases in-store, offering greater flexibility.

○ Increase digital marketing efforts to drive traffic to digital platforms and


utilize digital campaigns to promote online shopping incentives, especially
during off-peak seasons.

Ensure Sustainability: As consumer preferences shift towards more sustainable and health-
conscious choices, Tesco should accelerate its offering of sustainable products and plant-
based alternatives to cater to the growing demand in these categories.

● Actionable Steps:

○ Expand product ranges such as plant-based foods and environmentally-


friendly packaging options to align with evolving consumer trends.

○ Partner with suppliers who prioritize sustainable farming practices and eco-
friendly manufacturing methods.

○ Launch a targeted marketing campaign promoting Tesco’s sustainability


efforts and healthier product options, appealing to environmentally-
conscious consumers and health-focused demographics.

○ Track consumer demand shifts using data analytics to anticipate future trends
and adjust product sales accordingly.
9. Privacy Concerns of Big Data Analytics and Strategies to Mitigate Risks

Data Bias: Big data analytics can inadvertently perpetuate biases present in historical data,
leading to unfair practices, especially in decision-making processes such as making purchase
orders, setting prices, or loan approvals. If not carefully monitored, algorithms may make
decisions that disadvantage certain groups based on demographic, psychograhic, or
socioeconomic data.

Therefore, Tesco can adopt following strategies to mitigate the risk of unfair and
discriminatory practices:

a. Execute audits in their data collection and analysis processes.

b. Ensure algorithms are continuously tested and refined for fairness by using AI
frameworks that actively reduce biases in decision-making.

c. Tesco should engage third-party audits to review data collection practices and
ensure that ethical standards are being upheld.

Privacy Concerns: With the collection of large amounts of personal and transactional data,
consumer privacy stands at risk. Improper data handling or storage can lead to breaches of
sensitive customer information, violating privacy regulations

To adhere to privacy concerns, Tesco can adopt following strategies:

○ Adopt privacy-by-design principles, ensuring that privacy protection is


integrated into the business processes from the outset.
Enhance data encryption practices, ensuring personally identifiable
information (PII) is not exposed during data analysis or sharing.

○ Provide customers with clear options to opt-out of data collection and be


transparent about how their data is being used.
○ Regularly conduct privacy impact assessments to stay compliant with
evolving privacy regulations and best practices.

Security Concerns:As Tesco collects and analyzes large datasets, it becomes an attractive
target for cyberattacks. A data breach can lead to the exposure of customer information,
financial loss, and a damaged reputation. The increased use of cloud services and connected
systems also opens the door to such data related vulnerabilities.
Therefore, it is recommended that Tesco adopts following strategies to mitigate security
concerns:

○ Implement end-to-end encryption for data storage and transfer to prevent


unauthorized access.

○ Ensure that all data is stored in secure cloud environments with multi-
layered security protocols.
○ Use multi-factor authentication (MFA) for all employees accessing sensitive
data, ensuring an additional layer of protection.

○ Regularly conduct penetration testing and simulations of cyberattack


scenarios to identify potential vulnerabilities.

○ Educate employees on data security best practices and continuously update


them on mitigation strategies.

In an era of increasing data collection and analysis, it is crucial for Tesco to take a proactive
approach to address ethical, privacy, and security concerns related to big data analytics. By
implementing robust data governance, transparent practices, advanced security
technologies, and continuous employee training, Tesco can mitigate these risks effectively,
protecting both its customers and its reputation.
References

Tesco PLC. (2023). Annual report and financial statements 2022/23.


https://www.tescoplc.com/investors/reports-results-and-presentations/

Office for National Statistics (UK). (2024). Retail sales, Great Britain: March 2024.
https://www.ons.gov.uk

Zwitter, A. (2014). Big data ethics. Big Data & Society, 1(2), 1–6.
https://doi.org/10.1177/2053951714559253

Laursen, G. H. N., & Thorlund, J. (2016). Business analytics for managers: Taking business
intelligence beyond reporting (2nd ed.). Wiley.

Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.).
OTexts. https://otexts.com/fpp2/

You might also like