AI Chatbot and Web Crawler
Motivations and problematics of the project
The customer is one of the Middle East’s leading residency and citizenship advisories. They provide outstanding service, a smooth process, and transparency. Digital marketing is an important piece of the process, transforming traffic through different sources into qualified leads.
Digital marketing has evolved to merge with data science to create more intelligent and optimal solutions. The old approach used by the company is showing good results, feeding the sales team with strong leads every day. However, numerous processes are done in a traditional way that comes with an OPEX cost.
The old solution includes a chatbot embedded on the website, behind which there’s a team of operators engaging with every customer landing there. This manual process can cause lead loss due to late replies and involves a monthly recurring cost related to the operators. The data history of all the conversations between the operators and leads is backed up. However, no analysis was done to take advantage of this valuable information.
The company was also partnering with Sopro for lead generation and email automation, resulting in a “per contact” cost with no guaranteed results. The contact list provided by the partner has to be reviewed and cleaned by the marketing team, and then the lead assignment has to be done manually.
Salesforce is a one-stop-shop for the company’s sales activity. In order to fill these gaps, an upgrade of the digital marketing strategy was required.
The main objectives of the project are therefore:
● Creating a chatbot from scratch that will be able to answer messages following a predefined script or multiple scripts, prequalify the customer based on our KPIs and our buyer persona, collect data of solid leads and integrate them to Salesforce.
● Building Natural Language processing algorithms that will understand what the customer is asking, and reply based on the predefined script. The algorithm will keep on learning and will understand even when the customer makes spelling mistakes.
● Loading and managing scripts to analyze the best approach to interact with the customer and convert them into leads.
● Integrating the algorithm into the website and Whatsapp to act as a frontline salesperson.
● Crawling web resources looking for promising leads, pre-qualify them and sending emails.
● Automating follow-up emails to warm up the cold lead.
● Sales Script processes mining to analyze the different sequences of
scenarios through which run the different leads, cluster them using similarity metrics and display any correlation between their characteristics and whether the lead was qualified or not.
● Analyzing Google data and social network data to explore the nature of relationships between the different features and provide explanations about the fluctuation of performance of the different channels.