Lantern’s online-shop review

Fictional case

It is January 2027. Ana Lim wants a review of Lantern’s online shop for the second half of 2026 before she plans the new year. She has two questions: “Is the shop doing well?” and “What happened in September?” On 1 September a redesigned checkout went live on the website (the app was not changed); on 5 October a fix for a payment-page bug on mobile browsers was released. Lantern, its customers and every figure are fictional.

Lantern’s online shop, July–December 2026 (fictional)
Month	Web visits	App visits	Web orders	App orders	Average order value	New customers
Jul 2026	7,400	2,400	205	89	$41.20	182
Aug 2026	7,700	2,500	224	92	$40.80	190
Sep 2026	8,800	2,600	158	93	$41.50	141
Oct 2026	8,300	2,700	222	97	$42.10	188
Nov 2026	10,400	3,200	322	113	$47.90	291
Dec 2026	12,500	3,700	446	137	$55.30	414

Ana set four targets in July: a conversion rate (orders ÷ visits) of at least 3.0%, an average order value of at least $45, revenue of at least $15,000 a month and at least 35% of orders from returning customers. On 1 October she e-mailed a short survey to the 240 customers who had ordered in September; 79 replied. 44 agreed that “the new checkout was easy to use”, 17 were neutral and 18 disagreed.

You will turn Ana’s questions into measurable ones, calculate the shop’s KPIs, find out where September’s fall came from, judge how strong the evidence is and recommend what to do and measure next. Round as each question asks.

What you will produce

Ana’s questions restated as measurable questions, with the kind of analytics each needs.
The shop’s KPIs for the six months against Ana’s targets, including a correctly weighted average order value.
A diagnosis of September: how much conversion fell, in which channel, and what it cost.
An assessment of the survey and of other explanations for the fall.
A recommendation to Ana of about 200–300 words: what to do, and what to measure to know it worked.

Loading the project…