From a98d50396e101ba8eaf21f7a758d91f04e670159 Mon Sep 17 00:00:00 2001 From: "hannes.kuchelmeister" Date: Mon, 27 Apr 2020 11:02:06 +0200 Subject: [PATCH] add further research chapter --- 30_Thesis/sections/80_conclusion.tex | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/30_Thesis/sections/80_conclusion.tex b/30_Thesis/sections/80_conclusion.tex index 61828b9..ed45e21 100644 --- a/30_Thesis/sections/80_conclusion.tex +++ b/30_Thesis/sections/80_conclusion.tex @@ -19,17 +19,7 @@ Due to the scope of this thesis it was not possible to analyse all possible scen \section{Further Research} \label{sec:Conclusion:PossibleExtensions} -\begin{itemize} - \item How to optimise such that no need to search through all stored finished configurations is necessary? Something like tree like structure to cluster elements - \item How to model hierarchy and knowledge about product components in preferences? - \item Letting users set preferences for product functions (e.g. for a forest a recreation function, a productive function, a protective function, etc.). How does it compare to explicitly choosing preferences? - \item Does the assumption that the closer the configuration state is to a finished configuration, the less the satisfaction increase and the less difference among recommended configurations hold true? - \item Validating if satisfaction correlates with theoretical metric used in this thesis - \item Identification of too homogenous groups to use single person recommender. - \item Test more complex products with more attributes and characteristics. Do they see the same effect in regards to stored configuration and recommendation quality. - \item Evaluate different types of generating user score for configuration - \item Larger Groups - \item Modelling hierarchy and knowledge in group decisions for configuration - \item Approaches towards configuration that reduce complexity and guide users for setting preferences - \item Implicitly getting preferences -\end{itemize} +During the work of this thesis several new research possibilities came up. This section will name and discuss them. +First, further investigation can be done on how the approach of storing parts of the solution space behaves with larger products with a larger solution space and how performance can be optimised. Moreover, other methods of gathering preferences can be designed. A user might not need to enter all his preferences but only the most important once. Other ways of inferring preferences might be an area to look at, too. Moreover, the influence of different hierarchies in groups could be taken into account for decisions. This can be in terms of positional hierarchy but also in terms of knowledge about specific parts of a product. +Additionally, research can be undertaken to validate the offline satisfaction metric used in this thesis. How close does it correlate with actual user preferences? +Another possible extension area to look at is the identification of too homogenous groups as this was the weak point of the recommender and how this knowledge can be used to improve decision making. More complex products and different scenarios are another area to undertake research in. Last, research in validating the performance of the recommender in a real group settings and comparing it to group meetings without the aid of a recommender should be undertaken. \ No newline at end of file