The reason why we want to exclude the hot-selling items with stable ranking is that when the sales volume of a product is stable, its ranking will also tend to be stable. Amazon’s A9 algorithm will quickly help the product find its corresponding potential customers. If it is selected as a model for listing at this time, it has missed the best listing time and its sales volume is unlikely to exceed the hot-selling items with stable ranking.
Assuming that the seller records data at the same time (for example, recording data from 7:00 to 8:00 Beijing time for 10 consecutive days), taking the Body Stocking category as an example, the following conclusions about data fluctuations can be obtained through data analysis:
(1) Products with a ranking standard deviation of less than 50,000 can almost all find a stable search position in the A9 algorithm (that is, there will basically be a “Customers who bought this item also bought” recommendation column under the product).
(2) When the ranking standard deviation is greater than 50,000 and less than 100,000, a non-stable search position recommendation column will appear under most product listings (that is, there will be a “Customers who viewed this item also viewed” recommendation column under most listings, and its appearance ratio increases with the increase of the ranking standard deviation).
(3) If the ranking standard deviation is greater than 100,000, it is almost impossible to find a listing with a stable search position in the A9 algorithm (that is, there will be no “Customers who viewed this item also viewed” recommendation column below the listing).
Based on the above conclusions, find out the popular styles with stable rankings among many styles and then eliminate them.
Tips: In probability statistics, standard deviation is often used as a measure of the degree of distribution of statistical data, which can reflect the degree of dispersion of a data set.
There are two ways to quickly find potential styles.
One is the rising ranking products, that is, the ranking values show a rapid downward trend.
The other is the unstable ranking products, that is, select those products with good ranking performance but high ranking standard deviation values. The large fluctuations in the ranking of such products indicate that they have not found their suitable search position in the A9 search bar. On the one hand, it may be due to the insufficient operation level of the sellers of these products; on the other hand, it also means that the A9 algorithm has not yet accurately positioned the potential customers of the product itself, and there is still room for improvement.
After completing the above steps, sellers can select some potential models through data analysis, which should account for about 10% of the number of store products. However, given that the rate of hot-selling products is generally below 5%, it is necessary to do some streamlining work. At this time, you only need to monitor the ranking of potential models in real time. Once it is found that its ranking has a stable trend and its sales volume is high, the product can be determined as a hot-selling model and can be put on sale immediately.