Seed Data
Populations are defined by their seed data
Semilattice needs a small sample of data from the target population to make predictions. This page explains the data requirements and some core concepts which will help you to create good Populations.
Requirements
Populations require individual-level survey, poll, or questionnaire response data from the group of people the Population aims to model. Beyond the first sim_id column, each column should contain the group’s responses to a single option multiple-choice question.
Technical requirements
Semilattice accepts .csv
files which meet the following requirements:
- the first column must be titled sim_id
- the sim_id column should contain a unique number in each row
- there should be between 5 and 20 question columns
- questions must be between 3 and 300 characters long
- there should be between 25 and 3,000 respondent rows
- answers must be no more than 200 characters long
- answer cells can be empty, but no more than 5% of them across all columns
- there should be between 1 and 15 unique answers per column
Qualitative requirements & guidelines
Semilattice doesn’t check if your seed data follows these requirements and guidelines, but they are essential to creating effective Populations.
Good to know
These considerations are useful to bear in mind.
Seed data are not the only data
A Population’s seed data do not represent all of the information which Semilattice uses to make predictions. Most of the information comes from the Large Language Model (LLM) used by the Simulation Engine, with the seed data effectively selecting the relevant information from the LLM.
This means that you should think about the predictive power of the questions and answers in the seed data rather than the actual information contained in those questions.
Predictive power
A Population’s accuracy when predicting the answer to a new question is dependent on the predictive power of the questions and answers in its seed data. This predictive power varies depending on the question being predicted and is a function of how those seed data work with the Simulation Engine.
Predictive power cannot be predicted
Due to the black box nature of the LLMs used by Semilattice, it’s not yet possible to tell which seed data have more predictive power with certainty.
Building intuition around predictive power
An intuitive way of estimating the predictive power of a question is to think about how informative someone’s answer to that question would be. For example, knowing someone’s age tells you a lot more about them than knowing whether they prefer ketchup or mayonnaise. However, it’s also important to consider the purpose of the Population you are building. If you work in R&D at Heinz, the latter question will have more predictive power for the questions you plan to predict.
Question selection best practices
The subset of questions you include in your seed dataset has the biggest impact on the accuracy and predictive reach of your Population. These best practices will help you achieve the best results.
Maximise predictive power
Pick questions with the most predictive power for your research objective.
Minimise subjective overlap
Pick a diverse set of questions, minimising questions which reveal similar information. For example, the questions “Do you prefer ketchup, mayonnaise, or mustard?” and “What is your favourite condiment on french fries?” have a high degree of subjective overlap.
Maximise the number of questions and responses
While not strictly required, a dataset with 20 questions and 3,000 responses is recommended. Datasets of 1,000 responses and ~10 questions can also work well.