The one-time buyer problem is one of the most widely known challenges for retail e-commerce brands, as it is difficult to identify the potential repeat customers from only one purchase instance. E-commerce companies often acquire new customers in large numbers through intelligent marketing strategies, but it’s imperative to identify which of these customers are likely to repeat purchases.

Our objective of building a repeat buyer prediction model into LXRInsights, NetElixir’s proprietary customer analytics platform, is to anticipate potential repeat customers among the one-time buyers in the last two months’ duration. Our solution is twofold: one, brands can start accruing loyal customers, and two, retaining existing customers costs less than gaining new customers.

Understanding Your Customer’s Buying Behavior

Through LXRInsights, we track customer’s paths-to-purchase from the first point of attraction to purchase to determine what behavior leads them to conversion. The transaction data we collect includes the time and day that the customers made their purchase, the number of items in the cart, the average order value of the purchase, the referrer or the channel that led them to purchase, the device, and more. We interpret customer profiles from the transaction data that unveils the customers’ purchase patterns. Based on this profile, we use a machine learning model to predict whether a first-time buyer will repeat their purchase. 

Request a full demo of LXRInsights for a holistic understanding of how to grow your business responsibly with data-driven insights.

How Your Customer’s Purchase Journey Trains Our Machine Learning Models

LXRInsights needs key features of the customers’ online shopping behavior to train the model accurately. The accuracy of the model depends on the relevance of the features generated. The following list describes some of the features generated for this model:

1. Pageview information such as the total number of pageviews or average daily pageviews made before completing a purchase.
2. Visit action counts to determine the number of website visits per timeframe of the purchase cycle, from first website visit to purchase.
3. The order information, which includes product diversity, number of items in cart, and order value.
4. The top five browsers, top ten first and second referrers, top landing day of the week, top landing hour, and top checkout hour.

For a sense of how we segment this customer data, download our FACES 2021 report, which catalogs the online shopping behavior of high-value customers across ten e-commerce industries, such as food and grocery and online gifting.

Machine Learning Model

Machine learning algorithms come in handy to accomplish our objective of predicting potential repeat customers. By following the ritual of training ML models, we separate the data into two parts —Training Set to train the model and Test Set to test the model’s accuracy.

Pseudo Code of the Model

Below is the algorithm our model uses to predict the likelihood of repeat customers among first-time buyers:

1. Collect data from the past thirteen months.
   
2. Label the customers with repeated purchases as “Repeat Customer” and the customers with single purchases as “Non-Repeat Customer” for a baseline of your brand’s existing customers.
   
3. Chart relevant features of each segment’s path-to-purchase as outlined above.
   
4. Separate the data into two parts as Train and Test data.
   
5. Train the model by using a set of ML algorithms.
   
6. Measure the accuracy of the model by using Test Set data.
   
7. Select the model with the highest accuracy.
   
8. If the accuracy value is high, share the list of anticipated potential repeat customers.
   
9. Provide the features of the predicted customers that could be used to retain and retarget them.

Conclusions

We use the past transaction data to generate the relevant features of the customers and train the model. By understanding your customers’ buying behavior, your brand can better ascertain repeat customers among your current one-time buyers. You can then generate more personalized campaigns to re-engage these potential repeat customers with your brand and possibly convert more loyal customers.

Visit LXRInsights to request a demo of our customer analytics platform to better understand your new and repeat customers’ online shopping behavior.

References

1. Guimei Liu et. al. “Repeat Buyer Prediction for e-commerce” 2016, KDD August 13-17, San Francisco, USA.
2. https://www.custora.com/blog/four-steps-to-solve-one-time-buyer-prob

The post Repeat Customer Prediction of New E-Commerce Customers appeared first on NetElixir.

According to the National Retail Federation, about 83% of consumers plan to celebrate Mother’s day in 2021. NetElixir forecasts that this may be the biggest Mother’s Day yet for online sales, as we project that we will see a 30% YoY increase in e-commerce sales compared to last year. 

“The crisis has led to more compassion, a surge in value placed on family relationships, and a greater sense of thankfulness,” says NetElixir’s Founder and CEO, Udayan Bose. In turn, these sentiments will result in strong sales for Mother’s Day as families seek to connect with one another.

The following anticipated trends for Mother’s Day can help brands align their marketing strategy to the online shopping intent and rising optimism of their consumers.

Online Shopping Trends Expected this Mother’s Day

Demographic Segmentation

According to Global Data in the United Kingdom, female buyers contribute more than their male counterparts when it comes to Mother’s Day gifting. When looked at individually, male audiences opt more for confectionaries, as opposed to females, who tend to go with alcohol-related gifts. This year, gifts seem to center around indulgence, to give mom a well-deserved treat.

Online Purchases

A good number of consumers prefer purchasing online as opposed to visiting stores. This has indeed opened up avenues for brands to promote their products across digital channels like online search, social media, search and display paid ads, email newsletters, and social media posts. The number of opportunities available across the digital landscape allows small brands to better compete with larger brands for consumer’s attention — and their wallets.

NetElixir forecasts that mobile devices will drive 56% of all Mother’s Day purchases (up from 48% last year) and 72% of all searches. Additionally, we expect May 5th and 6th to be the biggest online shopping days for Mother’s Day purchases (in line with prior years where shoppers waited until a few days just before the holiday to make an order). We anticipate that buy online and pick up in store options will continue to be an important driver of online sales, as customers grew accustomed to this option throughout the pandemic months.

Comfort and Luxury Goods

As iterated earlier, working mothers have to fulfill a lot of responsibilities in their everyday lives, especially during these challenging times. A number of consumers are also opting for goods that can bring in a sense of comfort and hope into their busy schedules.

While consumers want to be comforted, they also have a greater sense of confidence as vaccination numbers continue to rise. Thus inspired, they are willing to spend more on non-essential luxury items. NetElixir expects this trend to continue during Mother’s Day, as it is the first big holiday where a large percentage of Americans are vaccinated. We anticipate people will buy more expensive items, especially in the apparel and jewelry retail categories; we forecast that the average order value will be 13-15% higher than last year and range between $238 and $240.

How to Target Different Types of Customers This Mother’s Day

Classic Mother’s Day gifts include flowers, chocolates, gift baskets, or a bottle of their favorite alcoholic beverage. According to Statista, 72% of buyers are expected to buy greeting cards, followed by 68% buying flowers, and about 49% are planning special outings to celebrate Mother’s Day 2021.

Within NetElixir’s dataset, we have seen fashion and jewelry sales experiencing a strong rebound as people start going out more and travel gains momentum. In Q1, online sales for fashion apparel were up 50% YoY and online jewelry sales were up by 35% YoY. In Q2, we believe these growth numbers will be even bigger (as Q2, 2020 was extremely slow for both categories). Online flower sales will peak this Mother’s Day – we expect 30-35% YoY growth for the online flowers retail category. 

Broadly speaking, we can classify purchase behavior into two types: conscious buying and impulse buying. 

Conscious Buying: In the conventional buying process, people take some time to do research, analyze competitors, and check pricing before arriving at their buying decision. Products that could be categorized under this bucket may include high-end gadgets like computers and laptops, phones, tourism packages, electronic gadgets, and more.

In order to target conscious buyers, one should target mediums where people are actively looking for product information like search engines, forums, or Quora Q&A for suggestions.

To tap into this segment, it is essential to streamline your site’s SEO, run paid search campaigns, and also participate in Q&A platforms to promote your brand and share your expertise.

Impulse Buying: Depending on the customer segment, there are goods that do not need much deliberation. Some of the products that fall under this category would include jewelry, apparel, books, toys for kids, beauty products, etc. For these types of products, social media ads, email blasts, and SMS campaigns prove to be effective to quickly capture a consumer’s attention.

Nearly half of consumers in Statista’s survey plan to buy mom a special outing for Mother’s Day. An outing is typically not an impulse buy, so travel agencies should heavily invest in offering holiday packages across paid search platforms. People actively search for and plan an outing, starting on a search engine like Google. Paid Search ads are the simplest and best ways to tap into this segment.

To engage the 35% of consumers in Statista’s survey who plan to purchase jewelry this Mother’s Day, it is important to tap into both paid and organic searches — where people are actively looking for products. Additionally, social and email platforms are great ways to reach out to users with discount deals and to drive a sense of urgency by adding countdowns to Mother’s Day or notify consumers of limited stock options.

On the other hand, those opting for the Mother Day’s staple of greeting cards and flowers are likely to be influenced by social platforms. Hence, the sellers offering these should leverage Facebook and Instagram ads so as to generate the curiosity element in the minds of users.

We believe Mother’s Day will kickstart a hyper-boom … and it will be the first event in which we experience real growth,” Udayan tells MediaPost.

Additional Last-Minute Tips For Brands!

Much of the Mother’s Day shopping continues to happen in the final three to five days prior to Mother’s Day, so sales may begin to pick up in the next few days as last-minute shoppers flock in.

Here are some quick handy marketing tips which you can adopt to boost your Mother’s Day product line:

1. Reward your customer with small Mother’s Day goodies.
2. Decorate your social media pages with the theme so as to generate a quick connection with your audience.
3. Share email/SMS blast with a prominent call-to-action URL pointing to a specific, top-selling product and or Mother’s Day-centric landing page.

Last but not least, just wish your customers well on the day itself. This will make users feel more connected with your brand and would surely go a long way to generate brand recall.

The post Mother’s Day Insights: Customer Shopping Trends appeared first on NetElixir.