Motivation of Workshop 

Nowadays, while most machine learning research on customer journey optimization has focused on short-term success metrics such as click-through rates or optimal ad placement, there has been little consideration given to developing a coherent system for end-to-end customer journey optimization. Such a system would encompass all aspects of the customer experience, from presenting the right product value to the right users, to understanding a user’s likelihood of conversion and long-term value to the platform, as well as their propensity for cross-selling and risk of churning.

Currently, models and algorithms for customer journey optimization are often developed in isolation, leading to inefficiencies in modeling and data pipelines. Furthermore, the customer is often viewed as a collection of different entities by different organizational departments (such as marketing, sales, and finance), which can lead to additional friction in the customer experience.

This workshop seeks to bridge the gap between academic researchers and industrial practitioners who are interested in building holistic solutions for end-to-end customer journey optimization. In addition, with the rising popularity of generative AI and LLM, we want to use this venue to exchange ideas regarding their applications in different stages of customer journey, and how the new technologies could help businesses achieve their KPIs.

4th Workshop on End to End Customer Journey Optimization (Topic, Audience, Relevance to KDD) 

For the holistic and long term success of a customer on a platform (Linkedin, NVidia, Databricks, etc.)- the key is to understand the levers that can help make customers more successful on the platform in the long term by estimating customers’ growth and retention patterns, lifetime value, interest to buy new products, propensity to churn, etc. Also, it is critical to not only predict success/propensities/lifetime but also be able to take the customer to a more successful path on the platform. Throughout the user journey and life cycle, there are interesting opportunities for customer optimization. 

• Broad Audience Brand and Product Awareness:
  • What is the best channel to invest for brand awareness?
  • What are long-term effects of brand tactics?
  • What value does brand and product awareness bring to the platform?
• First Time User Acquisition: 
  • Which user group is worth targeting via marketing and directing to purchase flow? 
  • Which ads creative and serving channel would generate the most likely conversions and customer value across multiple products?
  • How do we optimize bidding strategy to maximize scale at an efficiency guard-rail such as LTV/CAC? How to optimize bidding strategy to maximize profitability?
• New User Onboarding: 
  • How do we leverage LLM to personalize the onboarding experience in a cost effective manner?
  • How do we identify when a new user is struggling with product value? 
  • How do we leverage notification and paid levers such as promotions intelligently to move users through the monetization funnel? 
• Mature User Experience: 
  • How do we provide the best product experience to serve users’ needs via recommendation algorithm, search algorithm, pricing strategy,  incentives, segmentation? 
  • What’s the best way to communicate with our customers and keep them engaged? 
• Churn Prevention and Win-back: 
  • How can we identify users who are at risk of churning and provide the promotions that keep them stay?
  • How do we win back churned users with the right offers? 

The goal of the workshop is to provide a forum for industrial practitioners to share practical experiences and real-world challenges, while academic researchers can popularize state-of-art research. Collaborative discussions and knowledge sharing between academia and industry can be fostered, and KDD is the perfect venue for this discussion.

Although machine learning approaches have been widely experimented and adopted across organizations to solve various independent problems, time has come to look at these optimizations holistically, remove redundancies and put the customer in the front and center. With this goal, we aim to organize this workshop in KDD.

Submission Guidelines

We welcome extended abstracts (at least one full page) and full papers (up to 10 pages) excluding reference and appendix pages on ML and data science solutions for optimizing customer journeys, spanning sales, marketing, go-to-market, product experience, and monetization. 

Our focus is on comprehensive solutions for new user acquisition, user retention, churn prevention, upsell, cross-sell, pricing optimization, and more.

From a machine learning/AI perspective, this translates into interesting problems in the area of:

• Gen AI and LLM Applications in improving customer experience 

• Semi-supervised and multi-task learning frameworks/algorithms to handle complex prediction and optimization scenarios. 

• Deep learning networks to model end-end customer life cycle. 

• Embeddings and representation learning for customers and their related entities. 

• Reinforcement learning to iteratively optimize personalized policies for maximizing user experience. 

• Multi arm bandits to select the optimal design and content dynamically through explore-and-exploit. 

• Propensity scoring to target the customers who are ready to buy from you

• Uplift modeling to predict the effect of intervention on user behavior 

• LTV prediction to get a measurement of customers who are more likely to be successful.

• Causal inference: Understand LTV changing events

• Churn prediction to predict which users are likely to churn and design interventions accordingly

All submissions must be PDFs formatted in the Standard ACM Conference Proceedings Template. Submitted papers will be assessed based on their quality, impact, novelty, depth, clarity, and generalizability. For each accepted paper, at least one author must attend the workshop and present the paper or poster.

Accepted papers will be presented orally or as posters, depending on scheduling constraints. They will also be posted on the workshop website and may be published in the ACM Digital Library. Both full papers (up to 10 pages) and extended abstracts (at least 1 page) are accepted for submission.

Reviews are single-blind. Please include author names and affiliations in your submission. 

Committees

Organizing committee

• Hongying (Shadow)  Zhao 
• Bradley Turnbull
• Zhenyu Zhao 
• Mert Bay
• Anbang Xu
• Neha Gupta

Contact

All questions about submissions should be emailed to zzy287@gmail.com