Eureka Forbes, part of the conglomerate Shapoorji Pallonji Group, is currently one of the world's largest direct sales company known for its water purifier brand Aquaguard with a turnover of more than INR 30 billion. The company is estimated to have a customer base of 20 million across 53 countries. The company's distribution channel includes a direct sales force of dealers, institutional channels, business partner network and a rural channel across 1500 cities and towns in India. The company's previous customer acquisition model ensured that interested customers were individually visited for demonstration of the product and for completion of purchase. While this made the company a household name, it kept the acquisition costs on the higher side. With the imminence of online retailing, the brand had been taking steps to establish their digital presence and build a stable online sales channel. The company website (www.eurekaforbes.com) attracts online traffic from various sources such as organic searches, google ads, email campaigns, etc. The company has started to use this click stream data to build a rich database of visitor acquisition factors and behavioral variables such as session duration, device category, pages visited, lead forms filled, etc. using the Google Analytics Reporting API. The company identifies these visitors as potential customers and is actively deploying remarketing campaigns with optimism to convert them. While these campaigns have shown some success, they have resulted in substantially high retention costs. The business goal is clearly defined for the company - they want to target potential customers while keeping the cost per lead (CPL) as low as possible. For Kashif Kudalkar, the Deputy General Manager for Digital Marketing and Analytics, the task is to achieve better conversion at lower costs. This is achievable when the target audience is narrowed down to a sizeable number for remarketing campaigns.

VMware (VMW) is a listed software company with headquarters in Palo Alto, California selling products in the Software Defined Data Center that supports multiple devices, apps, and cloud to create an enterprise-ready cloud infrastructure. The company exclusively caters to business customers, that is, in the B2B environment. The company is characterized by 100% digital supply chain which implies that all products are downloadable from the website (www.vmware.com). The company also promotes these products online. Varied individuals across companies worldwide visit the site to familiarize themselves with the products and their features before making a decisive purchase. Along with the overview and use of the product, there are various customer-interaction triggers or ''digital assets'' that are shown to the VMW audience. These include triggers such as hands-on-learning, seminar/webinar registration, downloads, etc. Kiran R, the Director of the Data Science & Analytics team at VMW wants to know the optimal order of digital actions to be pushed towards customers to engage them effectively. Kiran's team has a rich source of online and offline available to model user's response to each of these digital assets. Kiran realized that the data is highly imbalanced and hence should be handled carefully. They wish to come up with a multinomial classification model for this purpose. Kiran decided that the model should fulfil the following objectives: 1. Determine the right order of digital assets to display to an individual e-mail id. 2. Since the website would like to target groups of e-mail ids, come up with a set of segment rules to identify top individuals for a digital asset and to target them with personalization on the website. 3. Have substantiated marketing and sales implications.