Key Takeaways from our Community Event
We recently held our monthly check-in with our Datacamp-Ishango.ai scholarship community. The event provided an opportunity to share knowledge, network, and explore the latest advancements in the field of data science. Two of our scholarship recipients, Rose Adeyinka and Albert Dellor, had the opportunity to present on a data science topic of their choice based on what they have learnt so far. Below, we delve into the key takeaways from the two presentations.
Rose discussed the importance of transforming raw data into meaningful intelligence to drive decision-making and propel organisations forward. She highlighted the benefits of transforming raw data, such as improving accuracy, identifying patterns and trends, predicting future outcomes, optimising performance, personalising experiences, mitigating risks, and enabling evidence-based decision making. Rose also explained the process of collecting diverse datasets from various sources and emphasised the need to identify data sources and define data requirements before proceeding with data acquisition and integration.
In Albert’s presentation, he highlighted how data can be used by supermarkets to cater to the ever-changing needs and preferences of their customers. Supermarkets constantly make changes, such as changes to store layout, product selection, pricing modifications, and promotional strategies, in order to stay competitive in the market and seize new opportunities. Albert demonstrated how the effectiveness of these transformations can be optimised by analysing customer purchasing behavior data. Based on a data set from a client, he discussed the steps required to extract these insights, including data wrangling, assessing data quality, and identifying missing values, duplicates, and outliers. Albert’s analysis delved into various aspects of the dataset, exploring daily transactions, popular brands, customer segmentation, and the average number of chips purchased by different customer segments.
Drawing from his analysis, he presented actionable recommendations to the stock owner, such as stocking preferred brands and sizes, bundling less popular brands with popular ones, and focusing marketing efforts on specific customer segments. Furthermore, Albert evaluated the impact of these recommendations by comparing the performance of trial stores to control stores during the pre-trial and trial periods. He explained the meticulous selection of control stores, initially similar to the trial stores, and conducted an in-depth analysis to determine significant differences in total sales and customer numbers between the two groups. Albert’s findings revealed significant improvement in the trial store during the trial period, underscoring the effectiveness of the implemented recommendations.
Together, the two presentations offered participants useful insights on the use of data to solve real-world challenges. Rose’s presentation emphasised the value of actionable intelligence derived from raw data, while Albert’s presentation showcased a practical application of data analysis in understanding customer behaviour and making data-driven recommendations.