CADiFIELD NOTES / PUBLIC DATABack to Case Studies ↗

UCI ONLINE RETAIL · REPORT 02 / 03

Growth arrived
as workload.

Autumn’s increase was mostly more orders, not dramatically larger baskets. A useful operating report separates throughput, timing and uncertainty instead of projecting one average into the future.

2010–2011 observations · 38 countries · report prepared 2 September 2026

+52.1%orders, September–November versus June–August 2011
+9.3%average basket value over the same periods
77.8%of orders recorded between 10:00 and 15:59, source clock

Real public retail data, not client data. Descriptive business intelligence, not causal inference. Positive-sale value is not settled revenue or profit. Business hypotheses and external research are labelled separately; no current-market benchmark is implied.

01 monthly orders

The autumn ramp is unmistakable.

All-country order groups. Amber highlights September–November 2011. Hatched December bars are partial source months, not like-for-like monthly comparisons.

Monthly positive ordersOrders. Zero baseline; hatched bars mark partial source months. Dec 10: 1,560 (partial); Jan 11: 1,093; Feb 11: 1,108; Mar 11: 1,460; Apr 11: 1,252; May 11: 1,686; Jun 11: 1,534; Jul 11: 1,476; Aug 11: 1,363; Sep 11: 1,838; Oct 11: 2,041; Nov 11: 2,772; Dec 11: 819 (partial)01,3862,772Dec 10partialJan 11Feb 11Mar 11Apr 11May 11Jun 11Jul 11Aug 11Sep 11Oct 11Nov 11Dec 11partial
Orders · zero baseline · scroll horizontally on small screens
Explore the exact figures
PeriodOrdersCoverage
Dec 101,560Partial source month
Jan 111,093Observed period
Feb 111,108Observed period
Mar 111,460Observed period
Apr 111,252Observed period
May 111,686Observed period
Jun 111,534Observed period
Jul 111,476Observed period
Aug 111,363Observed period
Sep 111,838Observed period
Oct 112,041Observed period
Nov 112,772Observed period
Dec 11819Partial source month

02 recorded value

More orders, plus a smaller basket lift.

Positive-sale value increased 66.2% over the summer-to-autumn comparison. This is recorded quantity × unit price, not settled revenue.

Monthly positive-sale valuePositive-sale value, GBP. Zero baseline; hatched bars mark partial source months. Dec 10: £823,746.14 (partial); Jan 11: £691,364.56; Feb 11: £523,631.89; Mar 11: £717,639.36; Apr 11: £537,808.62; May 11: £770,536.02; Jun 11: £761,739.90; Jul 11: £719,221.19; Aug 11: £759,138.38; Sep 11: £1,058,590.17; Oct 11: £1,154,979.30; Nov 11: £1,509,496.33; Dec 11: £638,792.68 (partial)0.00m0.75m1.51mDec 10partialJan 11Feb 11Mar 11Apr 11May 11Jun 11Jul 11Aug 11Sep 11Oct 11Nov 11Dec 11partial
Positive-sale value, GBP · zero baseline · scroll horizontally on small screens
Explore the exact figures
PeriodPositive-sale value, GBPCoverage
Dec 10£823,746.14Partial source month
Jan 11£691,364.56Observed period
Feb 11£523,631.89Observed period
Mar 11£717,639.36Observed period
Apr 11£537,808.62Observed period
May 11£770,536.02Observed period
Jun 11£761,739.90Observed period
Jul 11£719,221.19Observed period
Aug 11£759,138.38Observed period
Sep 11£1,058,590.17Observed period
Oct 11£1,154,979.30Observed period
Nov 11£1,509,496.33Observed period
Dec 11£638,792.68Partial source month

03 weekly rhythm

Thursday leads. Saturday is empty.

Total observed orders by weekday, not orders per open day. No Saturday orders are recorded; that alone does not prove the retailer was closed.

Orders by source-clock weekdayObserved orders. Bars start at zero. Monday: 3,129; Tuesday: 3,561; Wednesday: 3,699; Thursday: 4,252; Friday: 3,149; Saturday: 0; Sunday: 2,212Monday3,129Tuesday3,561Wednesday3,699Thursday4,252Friday3,149Saturday0Sunday2,212
Observed orders · zero baseline
Explore the exact figures
MeasureObserved orders
Monday3,129
Tuesday3,561
Wednesday3,699
Thursday4,252
Friday3,149
Saturday0
Sunday2,212

04 clock rhythm

Six clock hours carry most orders.

All-country order timestamps, 10:00–15:59 highlighted. These are invoice creation times, not website visits, staff hours or authorization events; timezone is undocumented.

Orders by source-clock hourOrders · hour of source clock. Zero baseline; hatched bars mark partial source months. 06: 1; 07: 29; 08: 566; 09: 1,486; 10: 2,367; 11: 2,398; 12: 3,223; 13: 2,756; 14: 2,461; 15: 2,348; 16: 1,342; 17: 669; 18: 192; 19: 146; 20: 1801,6123,223060708091011121314151617181920
Orders · hour of source clock · zero baseline · scroll horizontally on small screens
Explore the exact figures
PeriodOrders · hour of source clockCoverage
061Observed period
0729Observed period
08566Observed period
091,486Observed period
102,367Observed period
112,398Observed period
123,223Observed period
132,756Observed period
142,461Observed period
152,348Observed period
161,342Observed period
17669Observed period
18192Observed period
19146Observed period
2018Observed period

These weekday and hour charts are separate totals. They cannot reveal a Thursday-at-noon peak without a joint breakdown.

05 model stress test

The narrow model misses. The wider one is not yet validated.

Separate UK arrival-model cohort: 273 training days and 99 later holdout days, fixed UTC calendar-day windows. This is not the all-country BI population above.

Observed coverage of nominal 90 percent prediction intervalsShare of holdout days inside interval. Bars start at zero. Poisson: 7.1%; Negative binomial: 100.0%; Nominal target: 90.0%Poisson7.1%Negative binomial100.0%Nominal target90.0%
Share of holdout days inside interval · zero baseline
Explore the exact figures
MeasureShare of holdout days inside interval
Poisson7.1%
Negative binomial100.0%
Nominal target90.0%

Passing every day can still be uninformative.

The Poisson interval covered only 7 of 99 holdout days. The negative-binomial interval covered all 99; such broad coverage is not evidence of calibration. Compare width and coverage, not coverage alone.

Training variance was 16.6 times the mean, and holdout mean count was 1.64 times the training mean. Both dispersion and change over time matter.

No forecast is promoted. These results support testing time-varying count models, not deploying the wider interval as a calibrated capacity forecast.