ADS Capstone Chronicles Revised

5

for increasing conversion rate. It can showcase brand stories which may result in a high conversion rate. Pay-per-click campaigns allow users to target specific demographics, geographic locations, and user behaviors. Using different tools like Google ads can ensure they can use product ads to target customers.

examined this data using statistical models using a program known as the Social Set Visualizer (SoSeVi). The results demonstrated Nike can use social media data to anticipate sales more accurately. This implies Nike can enhance their performance and business selections by using social media analytics. e-commerce landscape is characterized by an abundance of consumer choices across multiple platforms, intensifying competition among retailers. To navigate this competitive environment, e-commerce platforms leverage the vast amounts of data collected from diverse sources. This data encompasses customer behavior patterns, product preferences, transaction histories, and transportation logistics. To harness the potential of this data, a multi-faceted analytical approach was employed, beginning with the setup of a dedicated MySQL database to manage and organize the data efficiently. A new database named ‘retail_database’ was created using MySQL to centralize the storage of various types of data, including customer information, transaction details, product information, logistics, and customer feedback. The database schema was designed to include tables such as ‘customer_info’, ‘transaction_details’, ‘transaction_logistics’, ‘product_info’, and ‘feedback’. Each table was structured to hold detailed information, ensuring comprehensive data coverage. To facilitate seamless data integration, primary and foreign keys, such as Product_ID, Transaction_ID, and Customer_ID, were used to join different tables. Data was collected and aggregated from multiple touchpoints within the e-commerce ecosystem, including consumer information, transactional history, product reviews, and shipping information. The primary dataset used for this analysis was the “Retail Transactional Dataset” 4 Methodology The current

3.5 Using Big Data Analytics and Business Intelligence for Improved Decision-Making at Leading Fortune Company

Olaniyi et al. have analyzed different leading fortune companies like Walmart, Toyota, Facebook, Netflix, Microsoft, Nike, and Meta to investigate their approach to big data and its analysis. Among them, we will highlight some of the important findings. Walmart: Walmart made a dataset with 45 Walmart outlets in various locations. This dataset includes weekly sales data and other variables like temperature, fuel price, unemployment rate, and holidays. They have used advanced data analytical tools like Hadoop MapReduce and Apache Spark for data analysis. Hadoop MapReduce is used for processing large data sets in a distributed computing environment, and Apache Spark offers a unified analytics engine for big data processing, including built-in modules for SQL, streaming, machine learning, and graph processing. These tools help with data processing, and analysis and uncover valuable insights about the company. Nike: Olaniyi et al. have tried to figure out how Nike could use social media data to make a better prediction on their sales. As they need to make the supply chain clean, and robust, they need to know how much sales of the product can be optimized for them to make after getting the sales forecast. To investigate it, researchers examined historical sales information from Nike's financial reports in addition to daily likes, comments, and posts on the company's Facebook sites. They

49