Competitive Advantage through Recommender Systems

By Chundyanto W.

It is hard to imagine the existence of e-commerce websites or any other popular entertainment and social media sites that do not utilize recommender systems nowadays. Recommender system is a technology to filter information in a website or a system in order to predict the rating or preference of a product for users. It has made a massive change in the way people interact with websites. In e-commerce websites, for example, users are easily guided to products they like according to their preference and taste based on their past shopping information. Another example can be taken from social networking sites, where users are suggested to connect with other users they may know based on their mutual interest, friends, or occupation. This improvement has certainly created a more attractive online experience for users by giving an ease of access through recommendations from the system.
Aside from providing an ease of access to guide users in interacting with a website, there are some other important benefits that are produced by the recommender systems. Recommender systems deliver relevant content to users because users will only be directed to items that match the users’ preference. This will lead to another benefit, which is assisting users in personalizing their profiles within the website. These efforts are meant to make users feel comfortable with the website, so that they will turn from just “regular shoppers, into loyal customers.” (Certona) Thus, not only it will increase customer satisfaction, but it will also help online businesses generate more profits from retaining customers.
Recommender systems can be classified into three categories. They are “Collaboration Based Recommender System,” “Content-Based Recommender System,” and “Hybrid Recommender System.” (Jones) First, collaborative filtering is constructed from users’ behaviors with similar traits. For example, users that buy book A are likely to buy book B, therefore other users that buy book A will be recommended with book B. Next, content-based filtering predicts users’ preference based on “the basis of a user’s behavior.” (Jones) Users that buy books about analytics, comment, and subscribe to analytics newsletter, will be suggested products or news that relate to analytics. Lastly, the hybrid approach is a combination of collaboration filtering and content-based filtering. This combination of approaches enhances the performance and usability of recommender systems in websites.
Some tools that functionalize recommender systems include LensKit, Scout Portal Toolkit (SPT), Recommender.org, and Duine Toolkit. To learn about how the tool works, we can take LensKit, a free open-source software to build recommender systems, as an example. LensKit allows us to create recommender algorithms through two main utilities, which are the “ItemScorer” and “RatingPredictor”. Based on the user’s profile, trait, and behavior, any numbers can be put into ItemScorer, then evaluated by RatingPredictor as an algorithm to determine whether the score matches or is similar to a related item. ItemScorer’s number can be based on purchase probabilities, which will then be scored by RatingPredictor to output the predicted ratings to determine the user’s preference and relation with a certain item. (LensKit) In addition, an interface called “Top-N recommendation” can organize recommended items that are scored in ItemScorer for users based on their user ID. (Lenskit) This way, an algorithm can be implemented into a website or a system to utilize recommender systems.
Big names such as Amazon, Ebay, Facebook, YouTube, and Netflix adopt recommender systems to be successful in their performance. To increase performance efficiency, most of these websites utilize the hybrid approach, or more than one recommender systems approach in their system. For example, Amazon uses the collaborative filtering to determine the likelihood of a customer with a certain trait to buy a product, as well as content-based filtering to narrow the product’s criteria to match the user’s preference. Netflix, the video rental and streaming service giant, flawlessly utilize the hybrid approach as well. It uses the collaborative filtering to see if users that watch a certain genre tend to watch the other genres or related movies. Collaborative filtering uses this information to make “individualized predictions.” (Bell, Koren, and Volinsky) Then it uses content-based filtering to narrow down the list of movies that may interest the user.
Tremendous functionality comes with a price, which applies to recommender systems. Although recommender systems work really well in terms of assisting users, there are challenges and limitations for the systems. First of all, a sufficient amount of data is needed to help predict users’ preference. It is hard for the system to predict a new user’s preference if the user only provides a limited amount of information and profile, especially if the user does not show a consistent pattern of behavior in the system. Changing user’s preferences can potentially be a problem as well. If the system only retains users’ past information, it will not recommend users based on their new preference. This will lead to a decrease in users’ satisfaction. (Muthukumar) Lastly, recommender systems are complex and can be difficult to implement.
It is clear that recommender systems open up a new challenge for online sites and businesses to compete for a competitive advantage in retaining their customers. Users always seek online experiences and transactions with websites that match their preference, which is mainly manipulated by recommendations from the system. Hence, websites with excellent recommender systems are likely to be successful.
Keywords: recommender systems, competitive advantage, benefits, limitations read more...

Read more

Analytics for Content Websites

By Jeffrey T.

Content websites, as their name implies, are sites dedicated to featuring content or information like news, articles, or blog posts whether it be in the form of text or multimedia. Given the diverse range of options for the types of content that can be posted, there is also a wide variety of analytics that can be employed to help maximize the visitor turnout, time spent on a page, and general web traffic. The purpose of utilizing analytics for content websites is to find out more about your users and the efficacy of your website in terms of its layout, marketing methods, and a whole slew of other categories in order to optimize and popularize your content.
For any website owner, using every form of analytics would yield the greatest returns whether they gather descriptive, diagnostic, predictive, or prescriptive analytics; however not all of them have the time nor the money to invest in them. Thankfully, there are free web analytics like the universally recognized Google Analytics, which is often more than enough information for most people or businesses. With the American Cancer Society, a 5.4% increase in donations resulted when they used Google Analytics to segment their traffic into three categories and cater to each one based on what they were seeking. Donors, event participants, and information seekers were recognized and tracked for their page views, substantial donations, or events completed through Search Discovery and Custom Dimensions: premiums of Google Analytics. Through analysis, they also discovered a large portion of their user base was mistakenly visiting their site during Breast Cancer Awareness Month, and, in response, they successfully redirected them to their Making Strides website with new promotions and links.
Focusing on their In-Page analytics feature, I found that Google Analytics successfully employs click analytics to help users identify and partition their viewers into groups. Every click tells us a little more about someone based on where they navigate to and the time they spend on certain pages. Other click analytics tools such as ClickHeat concentrate on heatmapping user clicks, which paint a more visually simplified picture of where users are clicking in a website using warm colors. The Kraemer Family Library site owner found that users constantly clicked on graphics near related text only to find out that they weren’t links, and made the appropriate corrections. Unfortunately, this type of mapping does not emphasize the numbers of clicks or give much information about who is clicking. By itself, ClickHeat’s use is limited, so it’s often paired with Piwik, another web analytics tool, as a plug-in.
If you decide to use these tools, you’ll still need to spend a substantial amount of time learning, and then using these applications for data analysis. There may be great flexibility within these programs, but nonetheless, it will be necessary to continuously spend time examining information collected, making the corresponding changes, and then viewing the results of those changes in a repeating methodical cycle to keep things up to date. Basically, the increased success of your content website will often prompt greater time consumption or resource allocation. Another issue could be the misunderstanding or misinterpretation of data. Analytics are fantastic tools for gathering information, but are better treated as supplements than complements, because it may be more necessary to learn the fundamentals of business and data first to properly use the analytics. A lack of understanding in those fields could lead to misusage of data and influence you to make suboptimal decisions or misinterpret trends as well as the meaning behind your data. This is not to say that these tools are flawed in that respect, but that we ourselves need to be proficient enough to avoid the common pitfalls in the vast library of information.
Overall, there is a great deal to learn with analytical tools and software; however, we must prepare ourselves just as thoroughly as we prepare the content on our website; otherwise we risk converting our assets into liabilities. read more...

Read more

Marketing Analytics

By Michael S.

Businesses have to do something to make sure that they are not wasting money. One way to help business not do that is to analyze market performance, it sees if the company is being efficient and maximizing effectiveness. Market analytics can also help find customer trends to see what customers are currently interested or what they will start to get interested into next. Also, with the advancing technology businesses have to use more than just web and social analytics to see make effective decisions, they need marketing analytics. With marketing analytics, they can get information over a span of time across all the other channels. read more...

Read more

Content Analytics with Content Websites

By Don T.

In today’s day and age, the playing field is constantly changing, whether it is the tastes of the consumers, or the trends that follow from a certain event or thought. In order to keep up with these changes, in order for companies to remain competitive in today’s world, and for other groups to keep and gain others’ interest for their group or activity, they will most likely do business with companies that utilize content analytics. By using content analytics, these businesses, groups, and individuals will be able to analyze and change as quickly as these trends do and to be able to keep and gain more audience members.
Content Analytics is a term used to refer to a variety of operations, including web analytics, content assessment, metadata tagging, social media monitoring, sentiment analysis, and text analytics (Seymour 2013). In short, content analytics refers to the analysis of the content presented on a web page, the data that is involved with it, what a user does whenever the data displayed on the page is accessed or touched upon by the user, and how the user reacts to the content that is on the page. The page is also analyzed with what users read the most, what users used to find the web page in question, what keywords were most important into drawing users to the web page, and what other content they searched for using that same page. It is the culmination of using many different types of analytics like Web Analytics, Visual Analytics, Social Analytics, Descriptive Analytics, and many more.
The benefits to using content analytics are that it will greatly improve a company’s ability to see how well their content is displayed, what solutions can be implemented should there be a problem with their display and their content, and that it can draw in more business and interested people. An example might include how an amusement park, like Disneyland, is able to set up their web pages in order to draw in those of whom are interested in either visiting or researching more information about the parks, hotels, restaurants, shops, and other venues they might like to come visit. If their page is set up in a way that works well with their users, it can draw in more people to visit their parks because of how well their information is displayed, how much information that the people using it receive, and how well the user is able to navigate about the website using their specified interests, such as “Thrill Rides”, “Fireworks show”, or “Character Greetings”. If the users are able navigate the pages easily and are able to use ideal keywords to bring them to the pages that they are looking for, their readers will be more influenced to make a visit out to the parks or surrounding hotels, shopping, and eating venues. The same could be done with news websites, such as FOX News or CNN News. FOX and CNN display news articles on their website, in which they use content on their page to tell the stories and specific keywords in order to draw in their desired readers. Once those readers have accessed the page in question, links to other articles that contain related keywords will begin to appear, in which case readers will be able to choose where they want to go if they wish to continue reading articles from that source. Using content analytics with these sorts of websites will help to greatly improve the quality of the content displayed and to help increase traffic to those pages.
Some examples of software programs that do content analysis are Google Analytics, IBM Watson, and Content Analytics. Google Analytics does more types of analyzations, such as web analytics, but web analytics is a tool that can aid in the analyzation process of content analytics. For example, if a website that has used web analyzation and visual analyzation is not doing so well with traffic, thanks to how the website is set up and because their visitors aren’t really reading the content on the page, the creators of the website could consider changing the layout and content of the website in order to draw in more visitors and increase its popularity. The company Content Analytics specifically uses “Enterprise level analytics tools for optimizing product content, keyword relevance & rankings in global e-commerce” (Content Analytics 2016). Content Analytics aids companies in using their analytics tools for helping customers with changing their content in order to draw in more customers and visitors.
The limitations of using content analytics for websites is that it is incredibly difficult to do. There are not many companies out there today that do website content analytics in today’s world. Another limitation is that it is extremely time consuming. Although there are companies that have produced software to accomplish this task in a shorter amount of time, it still takes a considerable amount of time to do. Web content analytics can also mislead companies about trends that are currently happening with their content, such as an article being something talked about in high volume like presidential candidates and their thoughts and not towards something that is less talked about in society, such as a localized natural disaster, like a flood or an earthquake. Another limitation is that web content analytics “… cannot tell us what people really think about these images or whether they affect people’s behavior” (Crossman 2016). This means that although companies can analyze the content, they will not be able to tell what the users and readers think about the content being published; they can only see whether it is being accessed in a high volume based on keywords or images sending them to the page with the content containing those keywords or images.
Although the method of content analytics has been around for many years, web content analytics is something that is highly sought after and will be for many years to come. In order to be able to survive in today’s market and internet geared society, groups, organizations, and companies will use content analytics in order to evolve their website content towards their desired readers, users, and customers. read more...

Read more

Analytics for SaaS

By Clanesha S.

One of the greatest innovations that has occurred in technology is being able to provide software applications over the internet. Today, businesses no longer find it necessary to physically purchase and install applications. Instead they are able to access applications by simply being connected to the internet. This breakthrough in technology is known as “Software as a Service” (SaaS). So how can businesses that incorporate SaaS know how grow their company? How can they come up with new ideas to increase revenue without having the burden of installing and managing software tools?
In order to answer these questions it is important to understand SaaS analytics and its importance. SaaS analytics is a web based software that collects data from organizations in order to improve their business. Analytics for SaaS based companies are usually based on monthly subscriptions meaning that a company can cancel their subscription at any given time. Some examples of SaaS based companies are (Google Apples, Salesforce, and Dropbox). In addition, SaaS based companies have immediate access to analytics which helps companies plan for a successful future.
It is important to mention that in order for SaaS based companies to survive today it is necessary to incorporate SaaS analytics. According to research published by Forrester the reason for the growth in SaaS is due to companies being driven by customer demands. In order for a SaaS based companies to know their next move it is important for them to focus on “what the customer is doing and what the customer wants.”
So how does a company incorporate SaaS analytics? There are many analytics SaaS providers such as Woopra, IBM, and GoodData. These providers’ helps companies understand and analyze trends, improve products, and provide the best solutions for success. While some analytic SaaS providers provide better features than others. It is important for SaaS based companies to determine which provider would be the best choice for their company. When a company receives data from analytic providers they are able to see key performance indicators such as subscription changes and know exactly how they can improve. A company can even get ahead of the customer by analyzing retention reports which shows how long until a customer cancels, upgrades, or downgrades their subscription. So a SaaS company that relies heavily on customers subscriptions can benefit from retention reports.
Also, there are many other benefits when a company incorporates SaaS analytics. Some of these benefits includes reduced cost, improve customer experience, instant access, and overall improvement of the company. In addition, with SaaS Analytics a company can determine how to increase revenue by choosing the right key performance indicators. In order for a company to choose the right KPI’s they must choose wisely and avoid analyzing to many KPI’s at once.
Tools that a SaaS based company might use for SaaS Analytics would be (Birst, GoodData, Tableau, or Google Analytics). While each of these tools offer different features they all share common characteristics. Each tool is able to track the movement of a customer, report revenue changes, offer many key performance indicators to choose from, and help companies improve their service. While there are many benefits of Analytics for SaaS it is important to point out that SaaS based analytics does possess a few challenges and limitations. Challenges include integration, security, performance, and functionality. Integration is a major issue SaaS analytics due analytics SaaS providers applications do not work with customers existing applications. In addition, some SaaS analytic providers have tried to come up with their own customary integration methods however the cost was expensive and the design was difficult. Another major problem is security. Yes! Security is a huge concern due to companies having confidential information stored on a cloud and former employees having access to the company’s analytics. For companies to restrict access it becomes a long process which some companies may fail to do. read more...

Read more

Managing the Marketplace: Marketplace Analytics

By Sloane C.

Marketplace analytics are, more or less, the information used in and behind the services for marketplace services. Marketplace services are places like care.com, angieslist.com, or even Uber and Lyft. Marketplace services provide very important services to help people out with specific, if sometimes mundane tasks, such as babysitters, drivers, people who may need freelance workers of some sort. And like most anything, analytics are incredibly useful for tracking what a business may need to do, what directions they can take their business in, and how to easily visualize data in easy to break down business terms. read more...

Read more

Software as a Service

By Jose T. S.

If the internet did not exist, imagine how much effort and production a business will spend without the applications and tools that exists today. Software as a Service, in short for SaaS delivers software applications to business enterprises over the internet using a pay per use (subscription) based revenue model. It is a tool that is established to maintain customer focus and faster business communication. read more...

Read more

eCommerce Analytics

By Daniel S.

The merging of the Internet with commerce has changed our world. The way we shop no longer requires one to enter a brick-and-mortar store hoping that what you need will be in stock – instead, everything that someone could want is only a button click away, and available 24 hours a day. So what allowed business transactions to leap to the digital medium? How did it evolve to where it is today? And how can we study the data it collects nowadays to make the most benefit? read more...

Read more

Visual Analytics

By Miguel R.

Visual analytics makes large amounts of data easier to understand by creating graphical interfaces, charts, data maps and other visuals. Companies like SAS and Appsee have developed software that allows users to analyze data using visual analytics to find correlations or patterns which helps solve issues and aid app developers in solving issues that their users experience, respectively. I will be explaining how visual analytics was used by both of these companies and some challenges they face when developing it. read more...

Read more

Visual Analytics

By Brendon Q

With today’s amount of technology, huge amounts of data is produced and collected throughout the world. Data can come in many different forms such as structured, un-structured, or a combination of both. It is very easy for data to be created. However, understanding the data can be very challenging. With the help of Visual Analytics, people are able to understand difficult data much easier. By definition, “Visual analytics combines automated analysis techniques with interactive visualizations for an effective understanding, reasoning, and decision making on the basis of very large and complex data sets”(D.A.). In this report, I will discuss how visual analytics is used and the challenges that comes along with it. read more...

Read more

Social Analytics

By Teresa P.

The technological advances of the 21st century has made a powerful impact on the way
the human race interacts socially and professionally. Most of what people do in developed countries integrates the internet in one-way shape or form. In our everyday life we go online to browse for our shopping needs or check up on our friends through various social media outlets. With 7 billion people on the plant and most having 2+ devices using the internet, can you imagine how much data is produced and consumed every second. It is almost impossible to keep track of and organize all that data. Once we do organize all that data, how can we use it? How can a business evolve efficiently using this data? One way a business can use this data to make intelligent decisions is through Social Analytics. read more...

Read more