Understand how categorical product attributes drive consumer choice. Upload choice-based conjoint (CBC) data, estimate part-worth utilities, simulate market shares, and find optimal product configurations — all in pure JavaScript, right in your browser.
Privacy: All estimation runs entirely in your browser. Your data never leaves your device.
Choice-based conjoint (CBC) analysis reveals how customers trade off product attributes when making purchase decisions. Each respondent completes multiple choice tasks where they select their preferred alternative from a set of products with varying attribute levels.
This basic tool estimates individual-level part-worth utilities for categorical attributes using multinomial logit (MNL) regression. For each respondent, the utility of alternative \(j\) in task \(t\) is:
$$ U_{jt} = \sum_{a \in \text{attributes}} \sum_{\ell} \beta_{a,\ell} \cdot \mathbb{1}[\text{level}(a) = \ell] $$
The first level of each attribute serves as the reference (utility = 0). The probability of choosing alternative \(j\) follows the softmax (multinomial logit):
$$ P(\text{choose } j) = \frac{\exp(U_j)}{\sum_{k} \exp(U_k)} $$
Coefficients are estimated by maximizing the log-likelihood with L2 (Ridge) regularization to prevent overfitting:
$$ \max_{\beta} \;\; \sum_{t} \sum_{j} y_{jt} \cdot \log P(j|t) \;-\; \lambda \|\beta\|^2 $$
This basic version is ideal when all your product attributes are categorical (e.g., brand, color, size tier, feature present/absent). It runs instantly in JavaScript with no dependencies.
Use the Full Conjoint Tool when you need:
Select a preset to auto-load realistic CBC study data, or upload your own CSV below. The download button lets you inspect or modify the dataset in Excel before re-uploading.
Upload long-format CBC data where each row represents one alternative in one choice task for one respondent.
Required columns: respondent_id, task_id, alternative_id, chosen (0/1), plus categorical attribute columns.
Or select a Marketing Scenario above to load example data.
Drag & drop CBC file
CSV with respondent_id, task_id, alternative_id, chosen, and attribute columns