Seminar in E-Business & Recommender Systems University of Fribourg, Department of Informatics Research Paper The impact of Recommender Systems on Business and Customers in Electronic Markets. STUDENT NAMES: José A. Mancera, Philipp Bosshard STUDENT NUMBERS: 10-801-207, 06-200-844 COURSE NAME: Electronic Business and Recommender Systems DEPARTMENT: Department of Informatics SUPERVISOR: ASSISTANT: DATE OF SUBMISSION: Prof. Dr. Andreas Meier Luis Terán 05-03-2015
56
Embed
Seminar in E-Business & Recommender Systems recommendations and suggestions for future work regarding the impacts of Recommender Systems on Business and Customers will be proposed.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Seminar in E-Business & Recommender Systems
University of Fribourg, Department of Informatics
Research Paper
The impact of Recommender Systems on Business and Customers in Electronic Markets.
STUDENT NAMES: José A. Mancera, Philipp Bosshard STUDENT NUMBERS: 10-801-207, 06-200-844 COURSE NAME: Electronic Business and Recommender Systems
DEPARTMENT: Department of Informatics
SUPERVISOR: ASSISTANT: DATE OF SUBMISSION:
Prof. Dr. Andreas Meier Luis Terán 05-03-2015
II
Table of contents
List of Figures ............................................................................................................. V
Trust User studies Qualitative Novelty Comparing recommendation list and user profiles, Counting
popular items Qualitative/ Quantitative
Serendipity Comparing recommendation list and user profiles, ratability Qualitative/ Quantitative
Diversity Diversity Measure, Relative Diversity, Precision-Diversity Curve, Q-Statistics, Set theoretic difference of recommendation lists
Quantitative
Utility Profit based utility function, study user intention, user study Qualitative/ Quantitative
Risk Depending on application and user preference Qualitative Robustness Prediction shift, average hit ratio, average rank Quantitative Privacy Differential privacy, RMSE vs. Differential privacy curve Qualitative/
Quantitative Adaptivity User studies but generally changing rate Quantitative/ Qualitative Scalability Training time, recommendation throughput Quantitative
Figure 11: Recommendation System Properties
Although there are many properties and we looked for papers that could include most
of these RS properties, there were not too many papers that could analyze or give
relevant evidence of interpretation other than accuracy, diversity and coverage
5.3 Evaluation Metrics for Recommender Systems
Evaluation Metrics or quality measures are a fundamental part to make a statement
about the quality of recommendation and prediction algorithms. The benefits of
evaluation metrics are that different Recommender Systems can be tested on
performance, compared with each other and improved. This stage provides an
overview about the most commonly used quality measures [7].
The evaluation metrics can be classified into 6 main groups. The first group consists
prediction metrics which are primarily used to test accuracy. Those are the Mean
Absolute Error (MAE), Root of Mean Square Error (RMSE) and Normalized Mean
28
Average Error (NMAE). In the second group, one can find the set of
recommendation metrics. Precision, Recall and Receiver Operating Characteristic
fall into that group. The third group deals with rank recommendation metrics. There
are two metrics which are the half-life and the discounted cumulative gain. Group Nr.
4 contains the diversity and the novelty of the recommended items. A fifth group
gives information stability metrics. Here, the use of the Mean Absolute Shift (MAS)
is proposed. The sixth and last group makes the use of Reliability measures [7].
Due the variety of options regarding the metrics, only the metrics that will be used in
Chapter 6 of this thesis are going to be presented.
5.3.1 Accuracy Metrics
Uis defined as the set of RS users, �̂�𝑢𝑖 as the set of predicted user-item pairs (u,i), 𝑟𝑢𝑖
as the true Ratings. The true ratings 𝑟𝑢𝑖 are known as they are hidden in an offline
experiment [6].
Mean Absolute Error (MAE)
Root of Mean Square Error (RMSE)
Normalized Mean Absolute Error (NMAE): The NMAE is a version of the MAE that
has been normalized by the range of (𝑟𝑚𝑎𝑥 − 𝑟min)
5.3.2 Privacy Metrics
Although in the recommender systems literature, there are many metrics definitions
to measure privacy, we find convenient to measure privacy with the k-anonymity
metric which is almost a standard in the context of Swiss Government Privacy. The
metric describes to which extent private information of the user is public. The
parameters of k-anonymity define the degree of anonymity. In the simplest approach,
the higher the value k, the more anonymity, otherwise values like k =0 means that all
private information is published in the Recommender System [19].
29
5.3.3 Adaptivity Metrics
The Adaptivity Metrics describe how fast the System can acquire new information
and can adapt it in the algorithm. Although this metrics can be measured by different
types of metrics, the one considered in this document is considered as changing
rate.
5.3.4 Trust Metrics
The Trustworthiness of a Recommender System cannot be measured in a
quantitative way. However, an often used approach is to conduct qualitative user
studies by asking the users whether the recommendations were reasonable to them.
There is the possibility to check how frequently a recommender is applied by a user.
A higher usage frequency is an indicator for a user to trust more in a Recommender
System [18].
5.3.5 Confidence Metrics
If we consider an online scenario, the confidence of a recommendation can be
calculated by the observation of environmental variables. Those so called confidence
scores indicate how frequently a recommender is used an applied by the user. Some
authors propose a calculation of confidences scores by using a neighborhood-aware
similarity model. The model includes similarities by users and items to generate
recommendations. The most suitable recommendation is the one that maximizes the
similarity between a recommended item and similar item. The usage of Confidence
scores can be applied by using confidence intervals or the probability that a value
predicted to the user is true [18].
5.3.6 Novelty Metrics
The Novelty Metrics measures the difference between the items recommended to
and known by the user. However, Novelty metrics do not have a standard. Bobadilla
et al. suggest the following formula used by various authors [7].
𝑍𝑢 represents the set of n recommendations to the user u. sim (i,j) refers to the
item-item memory based Collaborative Filtering similarity measures.
30
6. Correlation between evaluation metrics and impacts
After an extensive analysis on different research papers which are related to
recommender systems, we realized that in most of the cases the researchers present
papers in three general categories:
Technical Research Papers: Creating new or proposing variants of
algorithms
Applied Short Research Papers: Applying an algorithm for a case with
purpose of testing
Comparison Applied Research Papers: Applying different algorithms and
compare results.
In most of the cases they compare the results in performance of the algorithms by
analyzing the metrics and in a certain way a short description of these metrics used
by some algorithms with the properties related to them. The categories of papers
studied for this seminar are presented in Figure 12.
Recommender
AlgorithmsCASES
Results
Metrics analysis
Recommender
PropertiesImpacts
TEST Relation Relation Relation
Technical Research Papers
Applied Short Research Papers
Comparison Applied Research Papers
Consequences
Relation
Figure 12: Scope of our impacts analysis
However, as we can observe in the figure 12, the relation between the metrics and
the impacts has not been analyzed or mentioned in the studies. We found that in
most of the cases the interpretation of the results of the algorithms applied on certain
cases have absences of this analysis.
In this section we present a potential series of cases where the connection between
evaluation metrics and impacts is potentially present. On the one hand, in most of the
cases we will support our scenarios with some research papers references and on
the other hand there are cases that we consider to have some impacts but there is no
literature that support these assumptions, therefore these cases will be a suggestion
as a potential future work to continue the research in this direction.
31
6.1 Documented Scenarios
6.1.1 Impact of Accuracy on Online Time
Recommender
AlgorithmsCASES
Metrics
MAE
RMSE
NMAE
TEST Relation Relation RelationRS Property
Accuracy
Impact User
Online Time
Consequences
Keep Interest
↑ Visits
Buy
Figure 13: The impact of Accuracy on Online Time
Scenario:
The scenario presented in Figure 13 shows the proposed correlation from the metrics
that support accuracy to the Online Time impact and potential consequences on the
user side.
Key Assumptions:
Users who shop online have a low level of patience or time tolerance in terms
of waiting to receive the information, so the switching rate between websites
that provide the same service is very high.
A user that could not only find accurate results or receive a result after certain
amount of time will change the e-commerce platform provider.
Analysis:
The time to retrieve results as a performance indicator in the RS algorithms has been
documented and measured in different papers and it plays a main role to determine
the efficiency as we can observe specially in the reference [13], where they compare
the time performance of different algorithms 1-NN, 80-NN and Eigentaste-algorithm
on a case that recommends funny jokes to the user. The performance response
times are normally measured in milliseconds.
On the other side for our assumption 2, we found evidence on reference [14] about
the tolerable waiting time of users for computer response and we extracted the most
relevant findings in the figure 14.
32
Study Findings/Recommendations
Miller(1968) Delay of 2 seconds is the limit before interference with short term memory occurs
Nielsen(1993,1995,1996) Delay of 0.1 second is perceived as instantaneous success
Delay of 1.0 second is the limit for users ‘flow of thought to stay uninterrupted
Delay 10 seconds is the limit for keeping users ‘attention focus on the dialogue
Scheneiderman(1984) Delay of 2 seconds is the limit where response to simple commands becomes unacceptable to users
Figure 14: Summary of user's tolerable waiting time for computer response
In order to understand this case consider an example where an user is looking for a
particular flight itinerary for vacations and it chooses an online retailer but if the user
does not get a recommendation on time, he would rarely stay on the same page and
change into another provider to look again for the same flight itinerary. Based on the
previous studies, we can infer that an algorithm that is designed to provide accuracy
in the results, it is not successful if it does not show the recommendation to the user
in the waiting tolerance interval of the user.
Based on the evidence of the papers and the diagram in the figure 13, the online time
as an impact has some consequences for the user and although we cannot predict
the exact user behavior, we propose three different potential consequences that the
user can take as a next step:
Consequences:
Buy: The user simply gets the product.
Keep Interest: He finds the product but he does not buy it and keep interested
on it.
Increase the Number of visits: Regardless the user buys or keeps interest on
the product that he searches. The accuracy of the algorithm ensures the
success of the recommendations and increases the number of visits to the
page.
33
6.1.2 Impacts of Accuracy, Privacy and Adaptivity on User Preferences
Recommender
AlgorithmsCASES
Metrics
MAE
RMSE
NMAE
K-Anonymity
Changing Rate
TEST Relation Relation RelationRS Properties
Accuracy
Privacy
Adaptivity
Impact User
User Preference
Consequences
↑ Trust
↑ Visits
↑ Loyalty
Figure 15: The impact of Accuracy, Privacy and Adaptivity on User Preferences
Scenario:
As we reviewed in the recommender systems properties section, a recommender
algorithm can consider different kind of properties that are related to certain metrics
in this case we focus on the scenario where the recommender system focus on the
RS properties such as accuracy, privacy and adaptability in order to have an impact
on User Preferences.
Key Assumptions:
Privacy is very important for the user and any kind of misuse of the information
has a negative impact on the service that the user is using.
High accurate predictions let the user to continue using the system and have a
positive impact on the service.
A high changing rate in the recommended products give the sense to the user
that the recommender system is giving him the last products of the market or
that the system is freshly updated in the products that the e-commerce
platform is offering.
Analysis:
In this case we have mentioned in previous chapters the metrics related to the
accuracy such as: MAE, RMSE and NMAE. Nevertheless for properties as privacy
and adaptability the metrics that we consider to measure these RS properties are k-
anonymity and changing rate respectively.
34
In addition changing rate metric is related to the adaptivity of the algorithm in the
sense to measure the freshness of the data or external data elements that it is
considering for providing the recommendation.
Firstly, the assumption regarding the privacy relies on the potential risks to divulge
personal Information from the users in the recommendations because there is the
direct risk that someone will get information that the user wished to keep private. For
instance as supportive argument that we found in reference [15], it was found that
revealing identity information could lead to identity theft. There are also indirect risks
of re-identification finding information about a user in one system that could identify
her in another system. These elements cause a negative impact on the user that
modifies his user preferences in a negative way.
Nevertheless it is not sufficient to say that privacy can totally affect the user
preferences in the way that the user will stop to use the service. As an example taken
form reference [15], there is an important case analysis that supports this idea and it
comes from the situation where in 2004, Amazon’s Canadian site suddenly
accidentally revealed the identities of thousands of people, who had anonymously
posted book reviews. It turned out that authors were praising their own books and
trashing other authors’ books. The New York Times reported that “many people say
Amazon’s pages have turned into what one writer called ’a rhetorical war,’ where
friends and family members are regularly corralled to write glowing reviews and each
negative one is scrutinized for the digital fingerprints of known enemies.” To increase
the credibility of some reviews”, after these events the writers still used Amazon
services.
Secondly, the accuracy and adaptivity are very good complement properties to the
privacy in order to make an impact on the user in the user preference side in the
sense that if the recommender still provides good accuracy in the recommendations
and the freshness of the information is highly appreciate it by the user then he might
just be careful to not provide all his private information and still use the services of
the site. [16]
Finally, Based on the relation between the RS properties described above and the
user preferences, we consider that there are three potential consequences due to the
change of user preferences shown in Figure 15.
35
Consequences:
Loyalty: The user is more devoted to the product, if he higher preference.
Trust: The higher the User preference is, the more the user will trust in the
Recommendation.
Visits: The number of visits increase with higher User preference as he turns
into a buyer or stays an observer on the webpage.
6.1.3 Impact of Accuracy on Product Views
Recommender
AlgorithmsCASES
Metrics
MAE
RMSE
NMAE
TEST Relation Relation RelationRS Property
Accuracy
Impact Business
Product Views
Consequences CrossSelling
↑ Revenue
Up-Selling
Figure 16: The impact of Accuracy on Product Views
Scenario:
The scenario shows the potential impact of Accuracy Metrics on Product Views of the
user. As mentioned before in part 4.3 under reference [11], the impact of RS on
Product Views is somewhat ambiguous.
Here we present a duality effect:
An accurate Recommender System will decrease the time the user spends on
the webpage and therefore the Product Views decline.
The decrease in time that the user spends online catches the user’s interest to
view additional and differentiated products which increases the Product Views.
Assumptions:
We assume that duality effect referring to product views has a positive impact
on business in both cases.
Analysis:
In a Research Paper case for two top movie retailers in North America, a study about
the Impact of 3 different Collaborative Filtering Algorithms on Product Views was
conducted (Figure 17).
36
Figure 17: Average Items viewed for 1 Control Group and 3 Treatment Groups
In the study, the Average Number of Items viewed for a Control Group, to whom no
CF-algorithm was applied, scored 6.5464. For a treatment group where Purchased-
Based CF (“People who purchased this item also purchased”) was used, the Average
Number of Items viewed increased to 8.1684 associated with a p-value of 0.026 ≤
0.05 Error-Likelihood (statistically significant). Therefore, we can conclude that in the
little case described, the use of a Purchase-based CF-algorithm has a positive impact
on the amount of products views [11]. However, the use of view based CF only
increase the product views by score of 0.2070 and was statistically not significant.
The recently viewed algorithm implies a decrease of the item viewed by 0.3358.
Consequences:
Revenue Increase: The use of a Purchased-Based CF-algorithm seems to
have a positive influence on the Product Views. The increase of Products
viewed by users may therefore imply more potential buyers of products.
However, the relationship between Viewers and Buyers was not investigated
in the Research Paper study.
Cross Selling: If the product views increase, the user is very like to view also
ancillary items to his preferred product and will possibly buy them.
Up Selling: An increase of Product views can awake the customer’s interest to
buy a more expensive version of a product, an upgrade or an add-on. Up
Selling will be then an additional Revenue for the Business.
37
6.2 Non-documented Scenarios
6.2.1 Impacts of Trust on Product Sales and Satisfaction
Recommender
AlgorithmsCASES
Metrics
Similarity
TEST Relation Relation RelationRS Properties
Trust
Impact Business
Product Sales
Consequences
↑Prestige↑ Revenue
Impact User
Satisfaction
Consequences
↑ LoyaltyRepurchase
Figure 18: The impact of Trust on Product Sales and Satisfaction
Scenario:
Trust is an important determinant for Recommender Systems. Personal information
from the user is needed to give him suitable Recommendation in return. The trust a
RS needs to have from the user can be divided in two forms. Firstly, substantial
information of the user is essential to be able to give good recommendations.
Secondly, the details of an automated Recommender Systems are fairly visible to the
user. It is often the case that the user does not know how the recommendation is
being done for him. To be able to accept a recommendation, the user has to trust that
the recommendation has enough accuracy. There are three types of trust violations a
user consider: [15]
Exposure: Access to personal user data
Bias: Recommendation of users are being manipulated
Sabotage: The reduction of recommendation accuracy on purpose.
Key Assumptions:
The more a user trusts in the Recommendations System, the higher the user’s
usage frequency will be [18].
Analysis:
Based on the previous explanation of trust, the suspicion is that the level of trust can
either negatively or positively affect Product Sales and the User Satisfaction.
38
Consequences:
Of Product Sales:
Revenue increase
Prestige
Of User Satisfaction:
Repurchase
Loyalty
6.2.2 Impacts of Novelty/Confidence on Product Sales and User Preferences
Recommender
AlgorithmsCASES
Metrics
Sim(Items)
P-Values
TEST Relation Relation RelationRS Properties
Novelty
Confidence
Impact Business
Product Sales
Consequences
Popularity↑ Revenue
Impact User
User Preferences
Consequences
ReturnRepurchase
Figure 19: The impact of Novelty on Product Sales and User Intention
Scenario:
As mentioned in section 5.1.5, Novelty Recommendations refer to items about which
the user has not yet had knowledge. From the Business perspective, Novelty can
lead to additional Sales as the user discovers a new product which he gets excited
about and might purchase it. From the customer’s point of view, a new product might
have a positive impact on his preferences. However, if Novelty is viewed in an
isolated way, the user might only view the product but not purchase it. To be more
sure that Novelty has an effect on the user, one must consider Confidence at the
same the time.
Key Assumptions:
If a user discovers a new product and is confident with the Recommender
System (based on previous purchases) at the same time, he is more likely to
really buy the product which is positive for the User Preferences.
Analysis:
Although there was no evidence found in respected research papers, we can
conclude that if Novelty and Confidence are applied at the same time, the impact is
positive on the Product Sales.
39
Consequences:
Of Product Sales:
Increase in Revenue: The customer decides to buy the product which gives
additional revenue to the company.
Popularity: The user considers relies on the recommender system.
Of User Preferences:
Repurchase: If a user purchased a product under the condition that Novelty
and Confidence are together at the same time, then he’s likely to do the same
in future for a different product.
Return: When Novelty and Confidence are high but the user has not bought a
product yet, he might come back in the future which increases Product Views.
40
7. Analysis and Results
After the revision of the scenarios in the previous section, we arise to the point to
dedicate a chapter to analyze in details our findings and provide some observations
which are related to the correlation cases.
It is important to mention that in the previous section the scenarios presented had the
possibility to be documented by evidence found in previous research papers or case
studies. Nevertheless, there are some cases that cannot be still documented for the
moment but they are interesting to be analyzed.
In this chapter we mention briefly the cases which cannot be documented yet but that
are interesting to study in order to find more evidence and continue expanding the
correlations. Moreover, we add short observations on the cases that could be
documented in a short section.
Finally at the end of this chapter, we will summarize the relations among the different
metrics, recommender systems properties and impacts that are considered in our
seminar study.
7.1 Documented Scenarios
As we could observe in the previous correlation cases, on the one hand there is
enough evidence from the side of recommender system studies that mention a
relation between RS properties and their metrics in a technical interpretation, but on
the other hand studies from the side of consumer research field have an extensive
experience treating the impacts on users and their consequences such as user
behavior. In addition marketing in electronic business have also documented the link
between the impacts and their consequences in the business, like increment of
revenue, prestige or number or visits. The link between these different fields is
already experiencing an intersection and finding correlations becomes more visible
as the correlation cases described in our previous section.
7.2 Non-Documented Scenarios
Although there are many different recommender system (RS) properties identified
and quoted by several book references, only very few of them are mentioned or
applied in research papers. For instance, RS Properties such as accuracy,
41
confidence are among the most quoted in research papers rather than serendipity or
risk. In the recommendation section, we talk in more details about some particular
non-documented scenarios that can add a significant contribution and complement
the results of this seminar paper.
7.3 The correlation results between RS Properties Results and Impacts
The intention of this section is to show in more details our findings and potential
applications from our results and report our research contribution. Nonetheless,
before discussing our findings, applications and contributions, we would like to take
some time to come back to the figure 20, which was also shown in section 6, in order
to get back into the context and see clearly the directions of our results and
contributions.
As we described previously the three types of research papers categories found in
the course of our seminar research were mainly:
Technical Research Papers
Applied Short Research Papers
Comparison Applied Research Papers
We do not mention again the definitions of these three main identified categories but
it is important to emphasize the scope and the limit of the research paper
categories.(see figure 20)
Recommender
AlgorithmsCASES
Results
Metrics analysis
Recommender
PropertiesImpacts
TEST Relation Relation Relation
Technical Research Papers
Applied Short Research Papers
Comparison Applied Research Papers
Consequences
Relation
Figure 20: Research Paper Categories in Recommender Systems Field
Among all the categories, the research papers have in common that they could not
reach a deeper analysis with respect of the interpretation of the metrics or RS
properties with respect users or the business, they just limited to understand and
42
evaluate trade-offs on metrics to measure properties of recommenders and their
effect on the overall performance.
Moreover, based on the researcher’s profiles in the papers and their style to present
their results, we observed that they cannot make a deeper analysis on the effects of
the RS properties or metrics because they are limited on their expertise in the fields
such as Consumer Research or Marketing in Electronic Business and vice versa.
This fact is totally understandable and we are not saying that their research papers
are useless or with lack of results. Most of the researchers in the field of
recommender systems are involved in the computer sciences field and they are
somehow blind to see the correct direction to understand the effects of their
algorithms on the impact on business or users.
Based on the lack of direction, computer sciences or recommender system designers
still believe that the proper way of gaining such understanding of the impacts on
consumers or business is trying all the possible scenarios, different algorithms and
see the effects on the user or business. It is like trying to break the enigma
cryptographic machine trying all the 158 million combinations.
Maybe we exaggerated a little bit with this example but considering the scenarios
previously analyzed, we consider that understanding the proven consequences and
impacts from the side of marketing and consumer research can simplify the number
of scenarios that must be tested in order to understand better the impacts of
recommender algorithms on the users and business.
The Figure 21 suggests the direction of the recommender system design from the
side of consumer research, marketing and computer science fields.
43
Recommender
AlgorithmsCASES
Results
Metrics analysis
Recommender
PropertiesImpacts
TEST Relation Relation Corrrelation
Technical Research Papers
Applied Short Research Papers
Comparison Applied Research Papers
Consequences
Relation
Consumer Research and E-Marketing field Computer Science on Recommerder Systems field
Testing Assumptions
Suggested Direction of the Recommender System Design
Figure 21: Direction of the Recommender System Design
It is time to present our results and their interpretation in order to justify our previous
arguments. Figure 22 summarizes all the documented scenarios in one diagram:
Relations between metrics, RS properties, impacts and consequences.
RelationRS Property
Accuracy
Impact User
Online TimeKeep
Interest↑ Visits Buy
Metrics
K-Anonymity
Changing Rate
RelationRS Properties
Accuracy
Privacy
Adaptivity
Impact User
User Preference↑ Trust ↑ Visits↑ Loyalty
Metrics
MAE
RMSE
NMAE
RelationRelationRS Property
Accuracy
Impact Business
Product Views
CrossSelling
↑ Revenue Up-Selling
RelationConsequences
Consequences
Consequences
Figure 22: Relations between Metrics, RS properties and Impacts on Documented Scenarios
The Figure 22 displays all the founded documented scenarios with their relations and
their direction from the left to the right. On the one hand, fields like Marketing and
Consumer Research document extensively the relation between the impacts and the
consequences. On the other hand, computer scientists have documented extensively
the relation between the metrics and the RS properties.
44
Based on our documented scenarios the results show the missing correlation that is
present between the RS Properties and the Impacts (red arrow, figure 21). It is
important to mention that the relation found goes only in one direction (unidirectional)
and it does not go in the opposite one. For instance let’s see the case of Accuracy
causes an impact on Online Time, in one direction (left to right) we documented
already that the accuracy influences the user to remain more time on the website but
in the opposite direction (right to left) the reason that the user stays online on a
website does not necessary mean that the website has accuracy as a property.
The diagram in figure 22 helps for instance to the RS designers to know the
consequences of the metrics implemented by their recommender algorithms without
knowing the details of the consumer research theory but knowing the final
consequence effects on the user or business.
Marketers or managers for instance can select some desired consequences and
know which recommender algorithm metrics have the desired effect on the users or
business and buy or rely on a recommender algorithm that uses these metrics.
Our results show that finding the missing correlation between the RS properties and
impacts bring great benefits and increase the understanding not only of the impacts
of the business but it also reduces the complexity for recommender systems
designers to focus only on the metrics that create the desired effect on the side of
business or users.
45
8. Recommendations
The aim of the section is to offer a series of recommendations based on the previous
analysis, observations and results of this seminar document, in order that
researchers can continue in the direction as suggested in this document.
8.1 Variety in Recommender System Properties
In the meanwhile of our research paper seminar, we found several papers focusing
mostly on few RS properties such as accuracy or confidence. Testing not only the
performance of different algorithms brings a great idea of their overall performance
but also researchers should start to integrate in their research analysis where they
include more RS properties to complement their research or case studies.
In order to facilitate the test and design of new algorithms, we present research
suggestions from the marketing and consumer research side as non-documented
cases that can be tested in order to see if there is a correlation between the RS
properties and the impacts. These scenarios are based in the most documented
topics between Impacts and consequences among users and business.
8.1.1 Non-documented scenarios suggestions
The figure 23 present the relation between all the elements related to the non
documented suggested scenarios.
Metrics
SimilarityRelation
RelationRS Properties
Trust
Impact Business
Product SalesConsequences
↑Prestige↑ Revenue
Impact User
Satisfaction Consequences↑ LoyaltyRepurchase
Metrics
Sim(Items)
P-Values
Relation
RelationRS Properties
Novelty
Confidence
Impact Business
Product SalesConsequences
Popularity↑ Revenue
Impact User
User PreferencesConsequences
ReturnRepurchase
Link
Link
Figure 23: Relations between Metrics, RS properties and Impacts on non-documented Scenarios
46
The previous suggested scenarios are open to be expanded and they were
suggested from the point of view of marketing and consumer research. The
importance here is to find potential evidence that there is a correlation between the
RS properties and the impacts.
8.2 Perception of the User
Perhaps perception of the user is one of the most documented impacts in the field of
marketing and consumer research but still without a full understanding of it. As we
mentioned before, perception impact was not considered in this seminar document
due the complexity and all the wide variety of factors that involve the perception of
the user.
Future Recommender Algorithms that attempt to measure this characteristic should
be very robust and consider many different types of correlations among user
characteristics that are still not clear or still under investigation in the consumer
research field. Despite of the complexity to model this impact, the last mille in terms
of research direction in recommender systems should go in this way because once
an algorithm can predict the perception of the user, an algorithm can influence deeply
the particular human reasoning of each individual. (This situation is sometimes
documented as psychological manipulation).
8.3 New Research Questions
Meanwhile, we were analyzing and finding the different relations between the RS
properties and the impacts, we wanted to present as a part of our results a certain
kind of model that would allow us to understand in general if the success of a
recommender algorithm in terms to make a positive impact on the user or business
rely in the number of RS properties considered. Unfortunately given the nature of
research papers analyzed, they only consider a few number of RS properties and a
generalization is still too early to imply or deduce.
With the purpose to encourage future researchers, who have different knowledge
backgrounds like Consumer Research, Marketing and Computer Science, they could
look if there exist a linear or exponential behavior that can model the success of the
recommender algorithm on the impacts based on the RS properties considered.
The figure 24 shows the proposed models and the potential relation to prove
between the number of RS properties and the level of impact on users and business.
47
Level of Impact on the User
# RS Properties Considered0
Algorithm 1
Algorithm 3
Algorithm 2
Level of Impact on the Business
# RS Properties Considered0
Algorithm 1
Algorithm 3
Algorithm 2
Figure 24: Relation between RS Properties and their impact on Users and Business
48
9. Conclusion
The field of recommender systems is highly active and in constant evolution. On the
one hand researchers from the computer side field have focused strongly their efforts
to improve or create new algorithms and classify some of the their properties, but on
the other hand Consumer Research and Marketers have target their efforts to
understand the impacts and the behavior of the consumer.
At the end the final goal of the extensive study of recommender systems on the field
of electronic business is mainly focus to obtain a win-win relation between the
provider of a service (Business) and the customer.
After our exhaustive paper research, we detected an opportunity to create a good
synergy between two fields that seemed to be focusing their research in different
directions. As we presented in our results, both fields start to overlap each other and
based on this circumstances, we could find enough evidence that allowed us to
extend the interpretation of their research paper results and enhance their research
findings.
Furthermore, based on our results recommender systems designers, marketers or
consumer researchers can find easily the relations among the metrics needed in
certain scenarios to cause an assertive effect on the business or in the users as well
as they can also look at the desired consequences in order to have a clearer goal of
which algorithms should be applied.
Our seminar paper research gives a first approach of finding these correlations and
we are aware that there are much more relations to discover but it depends
enormously of the variety of RS properties tested in the algorithms. As long as the
diversity of studies in different RS properties increases, there will be more
possibilities for researchers to find more relations, which would allow them to refocus
their research in a better direction and discover interesting scenarios rather than
applying all their algorithms to all the possible scenario combinations.
49
10. Future Work
Based on the analysis, recommendations and conclusions presented in this seminar
document, it is important to mention the next steps or some research directions
derived from this paper. The next points represent a starting reference point where
researches can contribute with better interpretation results and continue with the
research of this seminar document. The next list mentions some recommendation
points derived from our research as a future work.
Researchers should start to test more variety of RS Properties in their papers,
rather than focusing on the most quoted RS properties such as accuracy and
confidence.
Continue their research of testing algorithms in the direction of testing the non-
documented scenarios proposed.
Research in the direction to find if there exists a relation between the impact of
the users or business vs the number of RS properties considered in the
algorithm
The perception of the user should start to be modeled in a more precise way
as long as the algorithms can take in consideration more properties without
compromising the performance of the algorithm.
Researchers should include Qualitative Analysis in their research.
50
11. References
[1].- Adomavicius, Gediminas, et al. "Do recommender systems manipulate consumer preferences? A study of anchoring effects." Information Systems Research 24.4 (2013): pp. 956 – 975 [2].- Chaffey, Dave. E-Business and E-Commerce Management: Strategy, Implementation and Practice. Harlow: Pearson; 2009. [3].- Ekstrand Michael D., Riedl John T., Konstan Joseph A. Collaborative Filtering Recommender Systems. Foundations and Trends in Human–Computer Interaction. Vol. 4, No. 2 (2010) 81–173 [4].- Jannach, Dietmar, et al. Recommender systems: An introduction. Cambridge University Press, 2010. [5].- Kowalczyk, Wojtek, Zoltán Szlávik, and Martijn C. Schut. "The impact of recommender systems on item, user, and ranking--diversity." Agents and Data Mining Interaction. Springer Berlin Heidelberg, 2012. 261-287. [6].- Rokach, Lior, Bracha Shapira, and Paul B.Kantor. Recommender systems handbook. Vol. 1. New York: Springer, 2011. [7].- Bobadilla et al. Recommender systems survey, in: Knowledge-Based Systems, Vol. 46 (2013), pp. 109-132 [8].- Beel, Jorean et al. Research Paper Recommender System Evaluation: A Quantitative Literature Survey, Magdeburg [9].- Lathia, N., Hailes, S., and Capra, L., The effect of correlation coefficients on communities of recommenders. In SAC ’08: Proceedings of the 2008 ACM symposium on Applied computing, pp. 2000–2005, New York, NY, USA, 2008. [10].- Joeran Beel, Stefan Langer, Marcel Genzmehr, Bela Gipp, Corinna Breitinger, and Andreas Nürnberger. Research paper recommender system evaluation: A quantitative literature survey. In Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation, RepSys '13, pages 15{22, New York, NY, USA, 2013. ACM. [11]. – Lee, Dokyun, Hosanagar, Kartik. Impact of Recommender Systems on Sales Volume and Diversity, in: Thirty Fifth International Conference on Information Systems, Auckland 2014. [12]. – Bambauer-Sache, Silke. Consumer Research 2014; Handout „Part A: Basic knowledge in the field of consumer research“ [13]. – Goldberg, Ken et al. Eigentaste: A Constant Time Collaborative Filtering Algorithm, University of California, Berkeley, IEOR and EECS Departments, 2000. [14]. - Nah, F. A study on tolerable waiting time: How long are Web users willing to wait? Behaviour & Information Technology, forthcoming, University of Nebraska-Lincoln, 2004.
51
[15]. – Karat, Marie-Claire, Blom Jan O., Karat John. Designing personalized user experiences in eCommerce, Human-Computer Iteraction Series Vol. 5, Kluwer Academic Publishers, 2004. [16]. – Lam, Shyong K “Tony”, Frankowski Dan, Riedl John. Do You Trust Your Recommendations? An Exploration Of Security and Privacy Issues in Recommender Systems, GroupLens Research, Computer Science and Engineering, University of Minnesota, 2005. [17]. – Bellogín, Alejandro et al. Report on the Workshop on Reproducibility and Replication in Recommender Systems Evaluation (RepSys), Centrum Wiskunde & Informatica, The Netherlands, Gravity R&D, Hungary, Universidad Autonoma de Madrid, Spain, 2013. [18]. - Robillard, M.P., Maalej, W., Walker, R.J., Zimmermann, Th. (Eds.) Recommendation Systems in Software Engineering. Springer Berlin-Heidelberg, 2014. [19]. - Federal Data Protection and Information Commissioner (FDPIC). Explanatory notes on Big Data, http://www.edoeb.admin.ch/datenschutz/00683/01169/index.html?lang=en, accessed on: April 29, 2015.