Introduction
In this project, I set out to analyze a dataset of products listed on Jumia, one of Africa's leading e-commerce platforms, with the goal of understanding how pricing strategies, discounts, and customer reviews influence overall product performance. Using Microsoft Excel, I cleaned and prepared the raw dataset, engineered new features to categorize products, ran correlation and trend analyses to uncover relationships in the data, and ultimately built an interactive dashboard to present the findings in a clear, business friendly format.
The objective was not just to explore the numbers, but to answer practical business questions: Do bigger discounts actually drive more customer engagement? Does price influence how a product is rated? Which products are genuinely performing well, and which ones might need a different pricing or marketing approach?
This article breaks down the full process behind how I turned raw data into a finished report from initial data cleaning to the creation of an interactive dashboard.
The following is the uncleaned data(original dataset)
Data Set Overview.
The dataset contains information about products listed on Jumia with the following columns:
•Product: Name of the product.
•Current Price: The current selling price of the product (in KSh).
•Old Price: The original price before discount (in KSh).
•Discount: The percentage discount offered on the product.
•Review: The number of customer reviews received by the product.
•Rating:The average customer rating of the product (out of 5).
Data Cleaning and Preparation
On a separate sheet after copy pasting the original data set I had to ensure there was no any present duplicate in the dataset.
Now that I had removed any duplicates that was present, next process was changing the cell format for each column from General to the appropriate data type i.e. Text for product names, Currency for prices, Percentage for Discount and Number for ratings and reviews.
Next, I used Find and Replace on;
- Both the Current Price and Old Price, replacing
"KSh"and replacing it with blank. - On rating category to correct it from
RatingdtoRating. - Replacing the
out of 5with blank in the review category. - Replacing blanks with
unknown
On both the Current Price and Old Price columns, there were highlighted cells (as seen in row 40 shown in the image below) containing a price range instead of a single value. To correct this, I used the =AVERAGE() formula to calculate the average amount on each cell.
The Review numbers were in negative values and reviews can't be negative hence so I used the formula =ABS() to remove the negatives.
I also used the =TRIM() and =CLEAN() functions on the Product column to remove extra spaces and non-printable characters that could interfere with sorting, filtering, or matching later in the analysis.
Below is the final Cleaned Dataset.
Data Enrichment.
I Created additional columns which would improve my analysis.
Discount Amount.
Formula used-
=(Old Price − Current Price).Rating Category.
Formula used-=IF(OR(F2="Unknown",G2="Unknown"),"Unknown",IF(G2<3,"Poor",IF(G2<=4,"Average","Excellent")))Discount Category.
Formula used-
=IF(E2<20%,"Low Discount",IF(E2<=40%,"Medium Discount", "High Discount"))Price Category.
I usedQUARTILE.INC()to create named breakpoints that split my Current Price data based on its actual distribution, rather than relying on arbitrary cutoffs.
I created two named ranges:
-
Price_Q1→=QUARTILE.INC(Cleaned!$B:$B,1)which is the 25th percentile, meaning 25% of products are priced at or below this value. -
Price_Q3→=QUARTILE.INC(Cleaned!$B:$B,3)which isthe 75th percentile, meaning 75% of products are priced at or below this value.
Using these two breakpoints, I then classified products into Low Price (bottom 25%), Medium Price (the middle 50%, between Q1 and Q3), and High Price (top 25%) using the formula:
=IF(B2<=Price_Q1,"Low Price",IF(B2<=Price_Q3,"Medium Price","High Price"))
The final Data set
Data Analysis
I used the formula =AVERAGE() to find;
- Average current price of products= KES1,187.
- Average old price of products= KES1,811.
- Average discount percentage= 37%
- Average product rating= 3.9
I used the formula =COUNTA() to find the total number of products which is 112.
To find the sum of total number of reviews I used the function =SUM()which is 723.
To find the most and least expensive products I used =MAX() and =MIN() which are KES 3,750 and KES 38 respectively.
Trend Analysis
I wanted to find out whether;
Higher discount percentage result in more customer reviews.
Using=CORREL(F2:F113,H2:H113)the correlation was r =-0.1368.
This means that there is a weak negative relationship between discount percentage and number of reviews. Hence as discount increases, reviews very slightly tend to decrease.Highly rated products receive more customer reviews.
Using=CORREL(I2:I113,H2:H113)the correlation between Rating and Review count was found to be 0.0572, indicating virtually no relationship. This suggests that review volume is not driven by product quality, but likely by other factors.Expensive products rated higher than cheaper product.
Using=CORREL(B2:B113,I2:I113)the correlation was 0.1100 indicating a very weak positive relationship. This indicates that more expensive products tend to be rated very slightly higher, but the effect is negligible. Price does not appear to be a reliable predictor of product rating.
while also;
• Identifying the top 5 products with the highest ratings.
Using the filter option on rating, I was able to filter the rating column to see the top 5 products as shown below;
• Identifying the top 5 products with the lowest ratings.
Using the filter option, I was able to find the top 5 products with Lowest Ratings.
Product Performance Analysis.
I was able to analyze the following using the filter option in the respective categories,
- Top 10 products with the highest discounts.
- Top 10 products with the highest number of reviews.
- Top 10 highest-rated products.
- Products with high discounts but low ratings.
- Products with strong customer engagement.
To identify products with strong customer engagement, I created an Engagement Category column that classifies each product into one of three tiers i.e. Weak, Average, or Strong which is based on a combination of review count and rating.
Rather than picking arbitrary thresholds, I used quartiles function
QUARTILE.INC()to set data driven cutoffs based on the actual distribution of review counts.
I created two ranges:
Review_Q1 — the 25th percentile of review counts
Review_Q3 — the 75th percentile of review counts
Then I used the formula: =IF(OR(H2="",H2="Unknown",I2="",I2="Unknown"),"",
IF(AND(H2>=Review_Q3,I2>=4),"Strong Engagement",
IF(H2<=Review_Q1,"Weak Engagement","Average Engagement")))
Then I filtered the Engagement column to retrieve Strong engagments as shown below;
Seller Performance Analysis.
Using the data i was able to answer the following by simply using filter.
- Which products appear to have strong customer demand?
- Which products may require better pricing or marketing strategies?
-Are there products receiving many reviews but having average ratings?
Using the Quartile Formula i was able to comeup with a review category and I used the formula =IF(OR(H2="",H2="Unknown"),"", to highlight the three tiers respectively hence allowing me to see the products being asked.
IF(H2<=Review_Q1,"Low Reviews",
IF(H2<=Review_Q3,"Medium Reviews","High Reviews")))
Hence deducing yes.
-Are there products with high discounts but low customer engagement?
Yes.
Dashboard Design.
Business Insights and Recommendations
At the end of this project, the following insights were drawn from the analysis:
1. Are higher discounts leading to higher customer engagement?
Not significantly. The correlation between Discount and Review count was -0.1368, indicating a weak negative relationship.This suggests that discounting alone is not an effective driver of customer engagement on this platform.
2. Do highly rated products have higher or lower prices?
There is only a very weak positive relationship, with a correlation of 0.1100 between Price and Rating. Ratings appear to be driven more by product quality or customer experience than by price point alone.
3. Which products are performing best based on reviews and ratings?
4. Which products may need improved pricing strategies?
Products which have weak engagements.
5. What recommendations would you give to Jumia sellers?
- Don't rely on discounting alone to drive engagement. Since discount percentage and review count showed almost no meaningful relationship, sellers should invest in other areas rather than assuming bigger discounts will attract more attention.
- Price is not a strong signal of quality perception. Moderately priced products can achieve ratings just as high as expensive ones, so sellers should not assume that premium pricing alone builds customer trust.
- Focus on products with Weak Engagement. Sellers should investigate why these products are not attracting reviews or interest as this represents the biggest opportunity for improvement.
- Encourage more customer reviews overall. Since review counts were generally low across most products, sellers could benefit from actively prompting satisfied customers to leave feedback, as review volume does not appear to be strongly tied to any single factor in this dataset.
GitHub repository link: https://github.com/wainainagabriel63-dev/Jumia-Product-Performance-Dashboard
Top comments (0)