The Interplay Between Online Consumer Reviews and Recommender Systems: An Experimental Analysis

February 14, 2017 carlaoz Leave a comment

We all know the situation: We are looking at a website to find the perfect product. A recommender system helps us sift through all the different options but we also take a look at customer reviews to make the best pick.

Recommender system have been found to be more useful (Senecal and Nantel, 2004) and to increase choice quality and confidence for a customer (Aljukhadar et al., 2012). At the same time, reviews from other users have been perceived as more trustworthy (Senecal and Nantel, 2004). So, what do you think happens when both, a recommendation generated by a system and previous customer’s review are available?

This is what the researchers Daniela Baum and Martin Spann (2014) tested during an experiment with 1332 participants of different age groups and gender from a large European country. Divided into 15 groups, the (informed) participants were asked to pick a gift for a friend on a hypothetical webpage. They picked one low-involvement product

(clock radio / package of coffee) and one high-involvement product (digital camera/ hotel stay). Depending on the group, participants received different information when making their pick, here some examples (also see cover picture): some participants did not receive any recommendation or review; for some, the provided recommendation and the review contradicted each other, while in other cases they supported each other. Now, let us take a look at the most interesting results of the study:

Unsurprisingly, if the recommender system’s suggestion and the customer review support each other, more customers follow the recommendation. This scenario is particularly effective for low-priced, low involvement products, because it simplifies decision-making and increases confidence in our choice (Aljukhadar et al. 2012; Baum & Spann, 2014)
A review which contradicts the recommendation or praises an alternate product (figure 1), significantly decreases the probability of following the recommender system’s suggestion on average by 30% for both, low and high-involvement products.
Negative reviews have the largest impact for experience goods. For example, when choosing a hotel, only 17% of participants still followed the system’s recommendation in the presence of a negative review compared to 68% in case of a recommendation and a positive review. The authors attribute this finding to the category “experience product” where previous customer’s experience is perceived to be more informative also considering the financial implications (Baum & Spann, 2014). While similar results were found for all the other products, only in this case results were significant.

What do these findings imply and why are they important? The results of this study show that by disclosing information wisely, firms can greatly influence decision-making influence customers. They decide about displaying reviews, how many will be shown and also which (type of) review will be made available. Still, firms are well-advised to keep showing negative reviews as well and must carefully consider them to maintain and improve customer satisfaction.

Would the findings of this study be the same in real life? It is likely, but this study is limited by the fact it lacks a lot of information which customer encounter in real-life: brands, different prices, different product looks, more information. The authors should have opted for an online experiment on a real platform; despite its drawbacks the results would simply be more realistic. Only further experiments and data analyses will be able to answer this questions fully.

Sources:

Aljukhadar, M., Senecal, S. and Daoust, C.E. (2012). Using recommendation agents to cope with information overload. International Journal of Electronic Commerce, 17(2), pp.41-70.

Senecal, S., Nantel, J. (2004). The influence of online product recommendations on consumers’ online choices. Journal of Retailing 80, pp.159–169

Baum, D., Spann, M. (2014). The Interplay Between Online Consumer Reviews and Recommender Systems: An Experimental Analysis. International Journal of Electronic Commerce 19(1). pp. 129–161

Cover picture:

Baum, D., Spann, M. (2014). Appendix 1 The Interplay Between Online Consumer Reviews and Recommender Systems: An Experimental Analysis. International Journal of Electronic Commerce 19(1). pp. 129–161

Articles

Technology Usage and Online Sales: An Empirical Study (De, Hu and Rahmad, 2010)

February 14, 2017 joshuakuijvenhoven Leave a comment

Many internet retailers offer their customers advanced technology features to enhance the shopping experience, such as search functions and recommendation systems. However, how do these technologies influence consumers’ shopping behavior? Does the way these consumers use these technologies influence sales or their purchasing patterns?

Information systems, such as search and recommendation technologies are used to enhance the customer experience, by reducing the steps required to come to a preferred product. Furthermore this systems help the consumer to discover products that they would not have sought out otherwise. In the consumer journey, the consumer passes the “information search” stage before the stage of “alternative evaluation” and “purchase”. And during this information search, consumers first try to activate prior knowledge, before acquiring external sources. There are two types of products: products that are displayed in a company’s advertisement, also called promoted products; or products which are not displayed in any advertisement, called non-promoted products. Some consumers search for a specific product, with an exact name. This is called “direct search”. Some consumers do not know where they are looking for and type just a word, like “dress”, this is called “non-direct search”. Consumers who look for a product with a direct search often used their prior knowledge.

Interesting to see, is that consumers who use direct search influence online sales, however, they only affect promoted products. This indicates that consumers who are encountered with promoted products through advertisements, use that prior knowledge to directly search for the products to purchase it. Furthermore, direct search is negatively related with non-promoted products. Furthermore, recommendation systems positively influence online sales, for both types of products. However, the recommendation system works stronger in categories with many products, than in categories with a few products. An explanation might be, it is likely that consumers lack prior knowledge of a large proportion of the product assortment and therefore find provided recommendations more beneficial. An unexpected finding is that non-direct search has no influence on consumers’ purchase behavior.

These findings are interesting for internet retailers, but it proves that it is beneficial to invest in advanced technology features, such as search and recommendation systems because this will lead to higher levels of sales. Furthermore, if online retailers want to increase sales via search systems it is suggested to also promote products because otherwise the tool only enhances the customer experience.

An example that successfully adopted these technology systems is Amazon. Amazon is one of the largest online retailers in the world that sells almost everything. Another advanced technology feature that Amazon uses is collaborative filtering systems, where the consumers get information about what other consumers bought after buying a particular product: “Consumers who bought this product also bought this…”. Unfortunately, this study has not included this technology feature. However, no worries, other research has proven that these systems also increases the diversity and amount of products purchased by a consumer (Lee and Hosanagar, 2015).

However, findings from this paper still show the importance of investments in information technologies, as it influences consumers purchase behavior. Furthermore internet companies are continuing to develop more sophisticated search and recommendation systems, which is a good trend.

De, P., Hu, Y.J. and Mohammed, R.S. (2010) ‘Technology Usage and Online Sales: An Emperical Study’, Management Science, 56, 11: pp. 1930-1945.

Lee, D. and Hosanagar, K. (2015) ‘People Who Liked This Study Also Liked: An Emperical Investigation of the Impact of Recommender Systems on Sales Diversity’, available online from: https://papers.ssrn.com/sol3/papers2.cfm?abstract_id=2603361 [14 February 2017].

Articles, Business Case, News

Who Has Time to Wait in Line? A Look into the World of Ritual

February 14, 2017 nzaifman Leave a comment

“The average office worker wastes 45 minutes per week waiting for coffee… and every millisecond counts.”

A Toronto based app seeks to please consumers and vendors alike by eliminating the need to wait in lines while still being able to purchase delicious food and coffee.

Ritual: allowing customers to skip lines while driving additional revenues to local eateries

In 2015, founder Ray Reddy noticed that wasted time can have a major impact on people’s decision making, so he decided to start a company that would be able to change that. He noticed that without all that wasted time people are more productive, efficient and happy. Ritual was founded to overcome these negative effects so people could stop wasting time waiting for coffee and get back to being happy.

How It Works

Ritual allows consumer to skip line-ups for takeout food and beverages. People working in offices or residing in certain neighbourhoods can order their food or drinks through the app and pay ahead of time with a credit card, which means no frustration with the credit card machine or unnecessary time wasted at the establishment. You can even customize your order on the app. As well, to increase people’s happiness by wasting less time, Ritual will notify the consumer when it is time to leave to pick up their order so it will be ready as soon as they arrive. The best part is when the consumer arrives at the establishment to pick up their order, there is no waiting, the customer is able to just walk up to the counter, grab their order and head back to work.

Business Model

Ritual’s business model works on the premise that starting small is the best way to get bigger. Ritual began in the King West neighbourhood, which allowed them to gain close relationships with each of the vendors to ensure a mutual trust and understanding. They were able to work with the vendors to ensure the new orders would not mess up their existing work flow. As well, the business model works in such a way that customers are not charged any additional costs for the service but rather, Ritual takes a portion of any incremental order revenues that are placed through the Ritual app.

Value Co-Creation and Efficiency Criteria

The method through which value-creation occurs is rapidly shifting towards a personalized consumer experiences (Prahalad, C.K., & Ramaswamy, V., (2004). In this way, value has been co-created with Ritual. Consumers are co-creators because they gain value from no longer needing to wait in line, but give value by providing additional business to the vendors which they otherwise may not have received. The vendors are co-creators because they provide the service to the customer, but gain value by receiving incremental sales. Lastly, Ritual was the medium that was able to facilitate co-creation because without them customers and vendors would have been worse off, but they are able to profit off the new symbiotic relationship they have created. It is efficient and meets the joint profit requirement because it gives incentives to all parties to cooperate. It is feasible and meets required reallocations because the polity is not related to the platform, the platform was made legal before it was launched, and Ritual will only accept credible merchants. Lastly, it is achievable because it is a new service with no true incumbents and it is scalable by neighbourhood (Carson, S.J., Dinney, T.M., Dowling, G.R., & John, G., (1999).

By Noa Zaifman, 468357

References

Prahalad, C.K., & Ramaswamy, V. (2004). Co-creation Experiences: The Next Practice in Value Creation. Journal of Interactive Marketing, 18, 5-14.

Carson, S.J., Dinney, T.M., Dowling, G.R., & John, G. (1999). Understanding Institutional Designs within Marketing Value Systems. Journal of Marketing, 63, 115-130.

O’Kane, J. (2015, December 16). Jump to the front of the line with this app. The Globe and Mail. Retrieved from http://www.theglobeandmail.com/report-on-business/small-business/sb-growth/the-challenge/need-for-speed-sparks-an-app-for-takeout-food/article27759031/