A decision engine helps users make choices by using personalized search results based on criteria such as online shopping preferences or tracked searches. It differs from a search engine, which is a centralized location for information. Decision engines use a decision tree to weed out choices and rely on user participation and community development to become more effective. Some models use accumulated search data to suggest results, and users can improve the results by providing feedback.
A decision engine is a type of web-based computer application that attempts to help the user make a decision in several ways. A common use case is online shopping, where a customer enters her priorities for a particular product and the decision engine determines which particular brands and models best suit her preferences. Decision engines can also work by tracking a user’s searches over time and using the collected data to make recommendations.
Decision engines are not to be confused with search engines. Search engines are a centralized location from which to access various information. Decision engines, on the other hand, produce personalized search results based on a number of criteria.
Instead of being a foundation from which a user can search, a traditional decision engine model aims to return its arguments as search results from other search engines. For example, a user might type a question into a search engine. One of the best results for this search would be a relevant topic about a decision engine.
Once on a decision engine, the user is presented with a series of questions, known as a decision tree, designed to weed choices on the path to finding the most ideal option. If a user was looking for cell phones, the questions most likely would be about price, size, carrier, and a desire for options like speakerphone, web features, and so on. Based on the answers to those questions, the highest scoring answer is finally presented with an accompanying explanation.
One major drawback of this decision engine model is that arguments must be created before they can be used. Similar to a wiki approach, such decision engines require user participation and depend on community development to become more effective. Decision engines that rely on human input are also subject to human subjectivity and opinion.
A common fix to biases in decision trees is to allow for community voting. The best or least subjective entries rise to the top, while the poorest entries are buried. The reliability of voting to undo poor entries also improves with greater community engagement, making it even more critical to have a large and active user base.
More automated decision engine models are built into popular search engines and work on the basis of using accumulated search data to suggest results that the user may find useful. Instead of relying on human input, these recommendations are produced on the fly according to predetermined formulas. Users can improve the results by telling the system whether they are useful or not.
Protect your devices with Threat Protection by NordVPN
