Yes you can. Our price optimization tool is based on reinforcement learning rather than neural networks, which means you don’t need huge amounts of historical data to get you started. Granted, the more historical data you have, the faster you can ramp up, but you definitely don’t need tons of data to get the ball rolling.

Yes. Sniffie collects each and every sales event from your Shopify database and studies what is the most profitable price your customers are willing to pay for.

Simple. You connect your Shopify Shop to Sniffie with three clicks and then select products you want to optimise. Sniffie will show you first price suggestions and ask for your approval before starting the optimisation. Then it’s fully automatic process. 

Yes. You can stop the optimisation process at any time. You will not be invoiced on that SKU anymore, unless you start optimising that again. 

In the best case, you get immediately a clear picture about the rough optimal level for your price points. The optimisation is based on reinforcement learning method and testing, so the more you have historical data, the more likely it is Sniffie is already on the ballpark once we start.

Sniffie will react also to market changes that are relevant. Meaning a sudden campaign of a competitor will not necessarily be enough for Sniffie to start optimising your prices. But if the prices drop significantly on the market Sniffie will notice it and start finding the new optimal price point. 

When it comes to marketing activities like digital advertising campaigns or newsletters, we can separate specific products from others and treat them differently from those with no ongoing promotion. But just like with digital marketing, things like website traffic are often poor attributes because you can never filter out all bot traffic and unengaged/irrelevant visitors. In fact, since the algorithm assesses a price point depending on if it’s sold or not, taking increased or decreased traffic numbers into account with no further information would often be misleading (e.g. if your marketing campaign attracted a lot of people with no real buying intent).

No matter your sales volumes, our tool’s pricing recommendations are always just as reliable. With lower sales volumes it just takes a bit longer for the tool to find the optimal price point.

No need to spend days (or weeks!) of work time each month monitoring competitor prices or adjusting your pricing strategies manually. Just plug in our tool and it will make sure you won’t ever again leave easy money on the table by not pricing your products proactively.

Don’t worry – our AI is no black box, actually quite the opposite: you have full visibility and control over anything and everything that happens at all times. If you wish, you can always opt to confirm price recommendations before going live. Optionally, you can also set safeguards to keep changes within preferred limits. 

Our reinforcement learning based pricing tool can increase profit margins equally well (according to our data, up to 10% on average, compared to manually set pricing rules) for high-end e-commerce brands, cut-price retailers with high sales volumes, and anything and everything in between.

While Sniffie can easily handle pricing for tens of thousands of products, we typically recommend businesses to start small and expand product use to long-tail products only after that. This ensures that you learn to make use of all the new data that you have at hand.

We offer a native integration on Shopify and easy-to-implement integrations with Magento (Woocommerce and other e-commerce platforms coming). If we don’t have an integration with your e-commerce platform, ERP or other systems yet, we’re typically able to offer tailor-made integrations that are easy to implement and don’t require too much of your developers’ time.

We’re so confident our tool works that we even have a money back guarantee! With our AI-based price optimization tool, e-commerce and retail businesses can increase profit margins by 5% during the first 90 days of use only (T&Cs apply), and on average 10% more compared to traditional methods of calculating price elasticity.