Archive for the ‘Product recommendations’ Category
We’ve been supporting email recommendations for a while now but it required our customers to use our apis which also meant – an “IT project”. We noticed that this approach creates a barrier for adoption of the technology and we thought that there must be a better way to add product recommendations to emails without pushing the integration burden to our customers.
We are excited to announce that in the spirit of our “zero integration” philosophy we came up with an innovative way that allows our customers to add personalized product recommendations to emails without any coding. And even better, our new product works with any email marketing platform that supports custom fields.
As a marketer all you need to do is login to your Barilliance account and create an email recommendations widget and then:
1. Select your email provider
2. Customize the widget if you want to
3. Copy and paste the HTML into your email marketing template
4. That’s it!
After you hit “Send” in your email marketing software , your emails will contain personalized product recommendations based on customers’ recent activity on your website.
Some of the online retailers we talk to, realize the value of cross-sells and up-sells and decide to embark on a “DIY path”. I may be biased here but I think product recommendations are one area in which you don’t want to reinvent the wheel.
There are 2 reasons why a DIY approach does not make sense in this case. The first is the development cost of building a system that works, and the second is the learning curve of optimizing it.
So how difficult is it to develop a recommendation engine? online retailers who decide to build a recommendation engine are not aware of the various components that need to be in place. Here are just a few them:
- The recommendation engine should track every major activity shoppers perform on the site including viewed products, categories and brands; items added to the shopping cart and purchased ; search keywords they used ; traffic source visitors arrived from, Geo-location data, and the list goes on…
- The system must support multiple recommendation types and should be able to display the right one (and more than one on a single page) based on where the user is at the purchase funnel (if you have less than 10 algorithms your system is extremely naive)
- Finding correlations between items/users is easy. The hard part is to choose which correlations should be taken into account and which should be ignored
- The system should have built in a/b testing and reporting capabilities so that it could be optimized and demonstrate its value. This point is very critical as few online retailers actually measure the impact of their homegrown systems
- The system should have an interface that allows marketers to control the outputs of the recommendation engine based on different variables.
The second reason I mentioned is the experience it takes to optimize such a system. There are many things that will determine the impact a recommendation engine will have on the business, and if it’s your first time building one and it’s a one-off project there is no chance you are going to know them or invest the time to learn them. In fact you are probably going to develop a very naive system and you’ll stay with v1 for a long time. You will not test different widget designs or various placements on the page.
The decision to build or buy a recommendation engine should be ROI based. You need to consider the impact it will have on your business versus the cost of development. Building a very naive system may seem cheap but will also likely to deliver poor results and without supporting systems you’ll never know it.
2. Another action you can take is to allow shoppers to get notifications when the product is back in stock. By doing this you engage customers and build up your permission based marketing database at the same time
3. Consider offering a coupon for first time visitors who landed on an out of stock page but purchased a similar product during the same session
- Trustworthiness as recommendations are not provided by the merchant. They are based on the “wisdom of the crowd”
- Transparency, shoppers are informed why products are being recommended to them
To show or not to show product recommendations on the shopping cart is always a question. While some retailers are concerned about interrupting the purchase flow others have been successfully increasing average order value using effective cross selling. If you do use product recommendations for cross-selling on your shopping cart, you want to make it as easy as possible for shoppers to add products without leaving the shopping cart page. Here are a few tips how to do it:
- Basic Product information – it’s important to show the basic product information including image, name , price, and available promotions. By not providing this very basic information you are probably driving shoppers to the product details page and you don’t want that.
- Additional product information – ideally shoppers would be able to open a popup which will provide more information on the product while staying the shopping cart page
- Add to Cart button – allow shoppers to add the product from the product recommendations section
- Availability - Do not recommend out-of-stocks products