a) Hello everyone, my name is Ravini Ravikumar. I am a current third year Bachelor of Commerce student, double majoring in Business Analytics and Finance. I am excited to join this course on predictive analytics and data analytics techniques. I have gained background in business analytics mainly through the various coursework where I worked on various projects involving data collection, analysis, and visualisation. For example, through a data visualisation and communication course where we had to create a data story based on an SDG. Through this project, I gained practical experience in handling large datasets and applying Tableau and R-code for visualisations. As well in another course, where we used r-code and predictive techniques. My personal learning objectives for this course include deepening my understanding of advanced predictive analytics techniques, learning how to apply these methods in real-world scenarios, and enhancing my skills in using tools like R.b)A compelling example of predictive analytics in action is its application in personalised marketing within the retail sector. Retail companies collect vast amounts of data on customer transactions, online behaviour, and demographic information. By leveraging predictive analytics, these companies can create highly personalised marketing strategies to enhance customer engagement and increase sales.For instance, a retail company might use supervised learning techniques such as classification and regression models to predict which customers are most likely to purchase a specific product. The response variable, in this case, could be the purchase likelihood of a customer, while the predictors might include past purchase history, browsing behaviour, customer demographics, and response to previous marketing campaigns. A commonly used model for this purpose is the logistic regression model, which helps in classifying customers into categories such as 'likely to buy' and 'unlikely to buy'.In practice, the company might collect data from its CRM system, e-commerce platform, and social media channels. It would use historical data. The results of the predictive model enable the marketing team to target high-potential customers with personalised offers and recommendations. For example, customers predicted to have a high likelihood of purchasing new electronics might receive targeted ads, discounts, or personalised emails.One of the potential drawbacks of this approach is the risk of overfitting the model to historical data, which might not accurately reflect future customer behaviour. Additionally, the model relies on the quality and relevance of the input data. To mitigate these risks, it's crucial to continuously monitor and update the model with new data and refine the predictive features based on emerging trends.