Sawtooth A&I Summit 2024: Explore the latest innovations in choice modeling with LLMs, conjoint analysis

Sawtooth A&I Summit 2024: Explore the latest innovations in choice modeling with LLMs, conjoint analysis
29 April - 3 May 2024
San Antonio, Texas, United States

Make a Breakthrough in Marketing Sciences

The Analytics & Insights Summit 2024 unites research and analytics professionals to deepen their knowledge and get hands-on training on the latest conjoint analysis methodologies. As long-time partners, SKIMmers will once again share their choice modeling expertise with industry peers at this Sawtooth conference.

Throughout the summit, our methods and analytics experts will present various academic sessions, workshops, and tutorials on a range of choice modeling, with a spotlight on AI: Large Language Models (LLMs) topics. Join our sessions and learn the latest conjoint analysis methodologies.

Running a pricing conjoint project from start to finish

Egle Meskauskaite Senior Manager
Remco Don
Director

Date & Time: 30th April, 14:00-15:30

Determining the optimal product or portfolio pricing has always been a critical strategic decision, and in light of the pricing dynamics we are observing these days, it is becoming even more important to have data-driven evidence to make these decisions. In this workshop, we will focus on the pricing (shelf) CBC study, and take a practical approach to guide you through the process.

What you will learn:

  • The tutorial will cover different pricing research approaches, including Van Westendorp, Gabor Granger, Monadic experiments, and Conjoint, and discuss the pros and cons of each method.
  • You will learn how to set up and analyze a shelf conjoint, including building a customized statistical design, data re-coding, counts, Logit, and HB.
  • The workshop will include tips and tricks to get the most out of the data, and help attendees model the data and interpret the results effectively.
  • The tutorial will be based on a real dataset using Lighthouse Software.

Choice modeling with LLMs and choice-based conjoint

Nino Hardt
Senior Director, Methods & Analytics

Date & Time: 1st May, 9:30-10:00

In this academic session, our AI expert, Nino Hardt, will showcase various applications of Large Language Models (LLMs) in predicting consumer preferences, drawing insights from real choice-based conjoint studies.

What you will learn:

  • Explore how fine-tuned LLMs accurately extrapolate average utilities from databases of tested concepts, providing valuable insights into potential market reception.
  • Understand how LLMs with self-explanatory capabilities can identify key drivers in consumer preferences, offering a deeper understanding of the factors influencing choices.
  • Learn how the synthetic respondent idea allows for the capture of heterogeneity in preferences, enabling not only the extrapolation of new concepts but also facilitating counterfactual analyses based on target customer characteristics.

A qualitative assessment of conjoint surveys: Unlocking respondent view

Egle Meskauskaite
Senior Manager
Remco Don
Director

Date & Time: 1st May, 11:00-11:30

In this presentation, we will delve into the intricacies of respondent understanding in online surveys, focusing specifically on conjoint exercises.

What you will learn:

  • Understand how the clarity of instructions impacts respondents’ accurate interpretation of survey tasks.
  • Examine the influence of anchoring on choices within conjoint exercises, revealing psychological insights and providing strategies to mitigate biases
  • Discover the impact of variety-seeking tendencies and the motivation to trial new options on respondent choices in conjoint analysis, gaining valuable insights for survey design optimization.

Surveys for Generation Z, evaluating various mobile-first designs

Joris van Gool
Manager

Date & Time: 1st May, 14:00-14:30

In this presentation, our expert will dive into enhancing the quality of a mobile questionnaire, aiming for a true “mobile-first” experience rather than just “mobile-friendly.”

What you will learn

  • Explore a range of improvements to elevate the quality of a mobile questionnaire, transitioning it to a “mobile-first” design for optimal user experience.
  • Investigate KPIs such as dropout rates and data quality, both in older studies and in custom research specifically crafted to prioritize mobile responsiveness.
  • Learn how to quantify the benefits of these enhancements and identify specific approaches to consistently improve the effectiveness of mobile surveys.

Respondent fatigue in choice-based conjoint – When and how does it affect the results?

Carl Johan Ekströmer
Senior Manager

Date & Time: 3rd May, 11:00-11:30

In this session, we’ll explore respondent fatigue in repeating CBC exercises.

  • Challenge common assumptions about respondent fatigue in CBC exercises.
  • Understand the methodology of stress-testing respondents through three studies with 32 tasks each and different levels of complexity.
  • Present the result of the tested respondent fatigue, highlighting limited implications for practitioners in CBC surveys.

About Sawtooth Software

Sawtooth Software provides advanced analytics and insights to help organizations understand what’s important to their customers and to predict what they will buy or choose. They do this through their solutions platform, consulting, and educational services.

The Sawtooth platform handles traditional survey questions, but they are best known for an integrated predictive analytics solution called Conjoint Analysis, or Choice Analysis.

Want to know more?

If you’re interested in learning how new research techniques can help you better uncover, predict and leverage the hidden truths behind decision making, please reach out. We’re happy to talk things through with you!