During the 6 day festival, Walmart increased its revenue by 155M Rupees as well as sold 435K additional products. analytical insights of promotional offers We found that out of all the promotional offers, items sold under BOGOF were seen to be the most successful as through BOGOF the festival saw 157,073 more units sold. Right next to this is the 500 Cash back promo which saw an extra 40,881 units sold. Whereas, items sold during this festival with the 25% off promotion performed the worse as it sold 5,717 fewer units than were sold without the promotion The BOGOF promotional offer generated an additional revenue of 69.3M as compared to pre-festival. Meanwhile, the 500 Cashback promo brought in 91M in extra revenue as compared to pre-festival. This means that although the 500 Cash back offer sold fewer units than the BOGOF offer we see that in the end it was still able to acquire a higher amount of extra revenue throughout this period. The primary reason for this is that the items applied to the 500 Cashback promo were far more expensive than those under BOGOF (i.e. furniture sets). The BOGOF promotional offer lead to an increase in revenue growth by 304% ⬆️and 500 $ CashBack offer by 139%⬆️. In contrast, the promotional offers of 33% off, 50% off, 25% off offer lead to a negative growth of 5% ⬇️, 39%⬇️ and 42%⬇️. we also observed the BOGOF offer to be the one that sold the most additional units and highest revenue growth. The 500$ Cashback offer also performed quite well. However, the discount offers such as 25% off, 33% off, 50% offer have shown negative revenue growth. Moreover, it appears that such discounts also failed to aid the company in being able sell a substantial number of units. Therefore, in the next festival we should only focus on utilizing the BOGOF and 500 Cashback promo and with that completely exclude the 50%, 33% and 25% off promotional offers. <br> Analysis insights of each campaign. Overall, products of the Grocery and Staples category sold the most while personal care products sold the least amount of units. This means there’s far more demand for Grocery and Staples category products. Throughout the Diwali festival we found that home appliances, home essential combo and home care products had on average sold an additional 30K units compared to pre-festival. In Sankranti, Grocery and Staples category products got sold by 109K more units as compared to pre-festival period. We can conclude from the above two insights that in Diwali people prefer to buy home essentials while in Sankranti they majorly buy items that is used in making staple food. This could be because, people know that there are high discounts on many products in the times of a big festival like Diwali. Moreover, many people also wait for Diwali to come so that they can buy what they need on discounts. And since, Sankranti is only of 1 day i.e 14 January, people majorly choose to buy daily staple food items as they pre-assume that they aren’t going to get good discounts on house items on such festival. On Sankranti, we generated extra 66 M $ and 334 K more quantities were sold as compared to pre-festival period. On Diwali, we generated extra 88M $ and 108K more quantities were sold as compared to pre-festival period. From the above two insights we can conclude that the majority of items sold in Diwali were far more expensive as compared to the majority of items sold in Sankranti . This is certain as in Diwali majority of items that got sold were Home essentials and in Sankranti, majority of items that got sold were staple food items. So, it’s recommended that in Diwali we should provide discounts on home essentials and in Sankranti we provide discounts on staple food items. Analysis insights for Stores and Cities Overall, top 4 stores in revenue generation are from Mystore(1), Chennai(2) and Bangalore(1) . In this stores we have seen maximum revenue growth in times of festival season. On an average we generated 4.5 M extra revenue and seen an average revenue growth of around 100% as compared to pre-festival time. Stores that are in Coimbatore have also shown 100% revenue growth, but the extra revenue generated from it was slightly less and was around 3.2M $ Similarly, we have seen a growth of whopping 260% on an average in quantities sold in times of festival season as compared to pre-festival times. On an average 12K more product quantities were sold from top 4 stores as compared to pre-festival days. Among all the cities in festival season, in Bangalore largest number of extra products were sold i.e around 108K in comparison to pre-festival times. On the other hand, in Trivandrum least number of extra products were sold i.e around 10K in comparison to other cities. Across all cities(including Trivandrum) on an average there was 200% rise in quantity sold in festival season. Among all the cities in festival season, in Bangalore we saw that largest amount of extra revenue was generated i.e around 38 M in comparison to pre-festival times. On the other hand, in Trivandrum least amount of extra revenue was generated i.e around 3M in comparison to other cities. Across all cities(including Trivandrum) on an average there was 80% revenue growth as compared to pre-festival season. RECOMMENDATIONS I will provide some recommendations based on the insights that I found previously while analyzing data. BOGOF and 500$ CashBack offer helped us in generating extra revenue as well as in selling huge amount of extra quantities as compared to pre-festival times. Thus, we should continue this offers in next festival season. On the other hand discount offers such as 25% off, 33% off and 55% off should be discontinued for the products on which we made this offer available in Sankranti and Diwali. This is because, all this offers lead to negative revenue growth as well as the fact these offers actually did more to hinder the company from being able to significantly sell more products than what normally would be expected during pre-festival times. We must ensure that in Diwali we provide discounts on home essentials and in Sankranti we provide discounts on staple food items.

in this analysis I decomposed the time series components and found that there was plenty of seasonality and little to no trend I then identified as well as removed outliers from there selected the 250 best-selling stores and ran a 60-week forecast followed by a 60-week forecast of the 250 worst selling stores

In this analysis I performed a conjoint analysis using dummy data to see whether respondents more so preferred NBA endorsed Athletic sneakers (Michael Jordan's sneaker brand vs Lebron James sneaker brand) based on features having to do with nostalgia or one that is more technologically enhanced

here is a conjoint analysis using dummy data focused on the imagined survey responses to the purchasing of a car based on the car's manufacturer or car model class type

Maven Toys Mexico City September 2023 performance dashboard

I coded a simple database using SQL based on the PC game Starcraft's Protoss faction in which I created tables representing a player's (who is protoss) infrastructure, tech tree, as well as available units, more advanced unit requirements alongside any basic to advanced upgrades whether defensive or offensive

here i did a statistical analysis using Poisson Regression to look for some connection between Covid-19 death and possible comorbidities

I performed an exploratory data analysis focused on finding patterns/trends for non lethal shootings in New York City ranging from 2006 to 2019. I assessed the count of shootings by borough, years, months, weekdays and each individual day of the month.

this is a dashboard focusing on the overall business of Addidas sales as well as reports focused on Addidas sales from each individual retailer

My first Dashboard using bikeshare data between 2023 and 2024

I used the customer_churn_tbl data set. This is a data set that looks at Churn, subscription tenure, monthly and total charges, in addition to dependents, gender, SeniorCitizen, Partner, Dependents, PhoneService, MultipleLines, InternetService, OnlineSecurity, OnlineBackup, DeviceProtection, TechSupport, StreamingTV, StreamingMovies, Contract, PaperlessBilling and PaymentMethod To analyze the outlook of churn: I used Kaplan Meier and Cox Regression.