Using the peekd dataset to predict the US retail ecommerce market


We used peekd’s ecommerce intelligence to predict the US Census Bureau’s estimate of the United States’ retail ecommerce market, in order to further analyze the US economy and consumer sentiment.

For Q2 2019, the Census Bureau reported $140bn of ecommerce sales. We predict this will be $144bn for Q3 2019 and $165bn for Q4 2019.


US Census Bureau data
For this study we used US Census Bureau unadjusted data from August 2019. This is an estimate of total retail ecommerce sales across the US, based on responses to the US Census Bureau’s Monthly Retail Trade Survey. These estimates are released on a quarterly basis.

peekd data
peekd’s dataset includes more than 100 million monthly transactions worldwide, across all industries. It includes $52bn of ecommerce sales in Q2 2019, roughly 38% of the total market as estimated by the US Census Bureau.

The correlation between peekd’s ecommerce intelligence and the estimates of US Census Bureau is 0.9, and gives an R2 of 0.8. This means peekd’s dataset mimics the rates of change present in the US data very closely.


Using two different approaches, we applied peekd’s ecommerce intelligence, in order to forecast the US retail ecommerce market.
In the first approach, we correlate the historical multiple of US Census Bureau data to peekd data, with the goal to estimate the US retail eCommerce market size. This would suggest a Q3 2019 market size of $144bn.

peekd measured a total of $54bn in retail ecommerce for Q3 2019. Historically, we observe that the US Census Bureau’s estimate is between 2.6x and 3.0x larger than peekd’s own estimate. We therefore multiplied the Q3 2019 peekd estimate 2.6 times (the average of Q2 2019 and Q1 2019 multiples) to estimate the Q3 2019 US Census Bureau ecommerce market size. Using the same approach, we can also estimate the US Census Bureau’s retail ecommerce data for individual months, or even weeks.

For the second approach, we forecast peekd’s dataset and then apply the multiples observed above to obtain a total market forecast. We used a decomposable time series model to forecast our time series, using an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. This predicts a US retail ecommerce market size of $144bn for Q3 2019 and $165bn for Q4 2019.


peekd’s ecommerce intelligence allows for more up-to-date insights into the United States’ retail ecommerce environment than the US Census Bureau’s data. This makes it a more responsive solution to understand consumer sentiment and the broader economic climate. Due to the high processing frequency and large dataset, peekd produces a superior model that renders highly predictive output.

peekd’s benchmarking solution allows for metrics to be broken down into more granular categories. This helps online merchants to make more data-driven decisions about their industry and customer demographics.

Create your free account and start growing with peekd today