A/B Testing - Gokwik 1.0 vs 2.0 plan

✅ Kerala Ayurveda Ecommerce

A/B Test Plan — Gokwik Checkout 1.0 vs 2.0

⁠

Objective (Hypothesis)

We believe that Gokwik Checkout 1.0 may deliver better business outcomes than Checkout 2.0 in terms of checkout reached to completed checkout %

⁠

Current Funnel Data (May 2025)

Sessions: 147,921

Sessions per day : 4930

Site conversion rate: 1.36%

Checkout reached: 4,108

Checkout completed: 2,012 → Checkout Completion Rate = 49%

→ Avg Orders/day ≈ 65/day

⁠

Test Variants

Variant A: Gokwik Checkout 1.0

Variant B: Gokwik Checkout 2.0 (current)

⁠

Used the following tool to calculate sample size

⁠

https://www.evanmiller.org/ab-testing/sample-size.html⁠

⁠

The 3 key inputs to calculate sample size:

Baseline conversion rate → In your case: Checkout completion ≈ 49%

Minimum uplift you care about (Minimum Detectable Effect, MDE) → Example: You want to know if 1.0 improves conversion by at least +10% relative So: from 49% → ~54.9%or 43.1%

Statistical power → Usually 80% — meaning "I want 80% chance to detect the true difference if it exists"

At 49% baseline, 10% MDE, 80% statistical power

we need 1632 sample size for each of the variation

⁠

Test Phases & Split

⁠

⁠

Metrics to Track

1. Checkout initiated

2. Login page CR%

3. Address page CR%

4. Payment page CR%

5. Checkout CR %

6. Prepaid % share of orders

⁠

Decision Criteria

If 1.0 shows: Significantly higher checkout completion rate i.e more than 5% relative positive difference without affecting the AOV negatively → Then roll out 1.0 at 100%

⁠

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.