Documentation — Conversion Tracking for Experiments

Welcome to Conversion Tracking for Experiments with Modern Pricing! You can track conversions for visitors in the experiment and control groups using our in-house A/B testing tool, which makes it easy to understand how Modern Pricing compares against your existing pricing strategy.

For Modern Pricing to start analyzing your experiment, first you have to install your conversion pixels.

Conversion Pixel Installation

Modern Pricing uses pixel-based conversion tracking. You can find your conversion pixels towards the bottom of your active experiment page.

Modern Pricing expects for the conversion pixels to be loaded on the page that marks a successful conversion. The example below may be used in combination with the Modern Pricing JavaScript snippet:

<script defer>
  window.onload = function() {
    function checkVariable() {
      if (modernPricing != 'undefined') {
        const experimentActive = modernPricing["a"]["experiment"].active;
        if (experimentActive == true) {
          var conversionPixel = new Image();
          if (modernPricing["a"]["experiment"]["variant"] == "control") {
            conversionPixel.src = "https://modernpricing.com/pixels/your-pixel.png";
          } else if (modernPricing["a"]["experiment"]["variant"] == "experiment") {
            conversionPixel.src = "https://modernpricing.com/pixels/your-pixel.png";
          }
        }
      }
    setTimeout(checkVariable, 1000);
    }
  };
</script>

For fully-complete experiment data, we highly recommend appending the conversion value on the end of the pixel URL, like the example below:

<script defer>
  window.onload = function() {
    function checkVariable() {
      if (modernPricing != 'undefined') {
        const experimentActive = modernPricing["a"]["experiment"].active;
        if (experimentActive == true) {
          var amount = 0.00;
          if (modernPricing["a"]["score"] == "low") {
            amount = 2.99;
          } else if (modernPricing["a"]["score"] == "middle") {
            amount = 4.99;
          } else if (modernPricing["a"]["score"] == "high") {
            amount = 6.99;
          } else if (modernPricing["a"]["score"] == "ultra") {
            amount = 9.99;
          } else {
            amount = 4.99;
          }
          var conversionPixel = new Image();
          if (modernPricing["a"]["experiment"]["variant"] == "control") {
            conversionPixel.src = `https://modernpricing.com/pixels/your-pixel.png?amount=${amount}`;
          } else if (modernPricing["a"]["experiment"]["variant"] == "experiment") {
            conversionPixel.src = `https://modernpricing.com/pixels/your-pixel.png?amount=${amount}`;
          }
        }
      }
    setTimeout(checkVariable, 1000);
    }
  };
</script>

When to Finish Your Experiment

We recommend finishing your experiment once the Chance to beat Control calculation (CTBC) has reached statistical significance.

Modern Pricing uses a significance level of 95%, meaning that CTBC has to be less than 5% or greater than 95% in order for us to report that one variant is outperforming the other.

If CTBC is > 95%, you can infer that your experiment variation is outperforming your original.

If CTBC is < 5%, you can infer that your original is outperforming your experiment variation.

What does "Not significant, need more data" mean?

If your CTBC is between 5% and 95%, it does not meet our threshold for statistical significance. If your score volume is low, gathering more data may prove that a significant difference exists.

Note: Modern Pricing only scores new visitors to your website in experiments. Only new visitors (as measured by IP address) to your website will be entered into experiments.