project:hotornot

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revisionBoth sides next revision
project:hotornot [2016/04/10 15:51] – [Hot or not for solar - Energy customer profiling made easy] erwinsaegesserproject:hotornot [2016/04/11 08:52] – [Team] cloock
Line 3: Line 3:
 > **Want to know who's hot** for putting a solar power system of his or her roof? > **Want to know who's hot** for putting a solar power system of his or her roof?
  
-> **Why spend unnecessary amounts of dollars** for unspecified and misdirected marketing+> **Why spend unnecessary money** for a non-specific and misdirected marketing effort?
  
 > We know **your next solar customer**!  > We know **your next solar customer**! 
Line 18: Line 18:
 ===Value proposition=== ===Value proposition===
  
-> For **energy service providers and utilities** who want to target specific solar power prospects our product **hot or not for solar** is an **energy customer profiling service** which produces a **prioritized list of customers** with an affinity for solar. Unlike traditional approaches our service takes advantage of hidden information from social demographic and economic values and uses machine learning algorithms for deriving the prospects affinity. In order to improve our algorithms we run surveys (quizz)injected in popular websites such as "20 Minuten" or our customers.+> For **energy service providers and utilities** who want to target specific solar power prospectsour product **hot or not for solar** is an **energy customer profiling service** which produces a **prioritized list of customers** with an affinity for solar. Unlike traditional approaches our service takes advantage of hidden information from social demographic and economic values and uses machine learning algorithms for deriving the prospects affinity. In order to improve our algorithms we run surveys (quizzes) injected in popular websites such as "20 Minuten" or our customers website.
  
 >> Simplified: For **utilities** who want to target specific solar prospects, **hot or not for solar** uses social data and machine learning to derive a **short list**. >> Simplified: For **utilities** who want to target specific solar prospects, **hot or not for solar** uses social data and machine learning to derive a **short list**.
Line 30: Line 30:
 ===Further potential customers are=== ===Further potential customers are===
  
-  * Public institutions such as Cantons and Municipalities how want to tailor information/communication/projects +  * Public institutions such as Cantons and Municipalities who want to tailor information/communication/projects 
-  * Planning and engineering companies / product developers how want to develop and sell new products+  * Planning and engineering companies / product developers who want to develop and sell new products
  
  
Line 38: Line 38:
 === Data === === Data ===
  
-BEN Energy (https://www.ben-energy.com) provided a sample data (approximately 5000 records) set with information about utility customers to include social demographic and economic information.+BEN Energy (https://www.ben-energy.com) provided a sample data set (approximately 5000 records) with information about utility customers which included social demographic and economic information.
  
 For detailed information see here: [[project:hotornot:Data]] For detailed information see here: [[project:hotornot:Data]]
Line 44: Line 44:
 === Goal === === Goal ===
  
-The main goal of our project was to test whether social demographic and economic information is value add in order to determine potential new solar customers. For background information about the business goals see section **Value proposition**.+The main goal of our project was to test whether social demographic and economic information is of value in determining potential new solar customers. For background information about the business goals see section [[project:hotornot#Value proposition|Value proposition]].
  
 === Method === === Method ===
  
-In order to test the hypothesis the team used **Microsoft Azure machine learning** and **R** (both using random forest algorithm). Furthermore the teams tested which attributes have most influence on the results. In parallel team members put together a list of properties they thought would influence the results. After a first iteration, falsifying attributes were removed from the machine learning process.+In order to test the hypothesis the team used **Microsoft Azure machine learning** and **R** (both using random forest algorithm). Furthermore the teams tested which attributes have most influence on the results. In parallel team members put together a list of properties they thought would influence the results. After a first iteration, extraneous attributes were removed from the machine learning process.
  
 Finally the team concluded the project by creating a website to showcase the machine learning result as well as the business view. Finally the team concluded the project by creating a website to showcase the machine learning result as well as the business view.
Line 54: Line 54:
 === Results / Findings === === Results / Findings ===
  
-The team was able to derive a specific list of customers with an affinity for solar. Based on the results it came to the conclusion that social demographic and economic play a secondary role though. However, with a larger and probably more accurate set of informationthe social information may become more important. For interest groups and businesses, the team recommends doing further research.+The team was able to derive a specific list of customers with an affinity for solar. Based on the results the conclusion was that social demographic and economic data play a secondary role. However, with a largerand probably more accurateset of information the social information may become more useful. For interest groups and businesses, the team recommends doing further research.
 ===== Team ===== ===== Team =====
  
Line 60: Line 60:
   * Christian Eggenberger / eggenberger@afca.ch   * Christian Eggenberger / eggenberger@afca.ch
   * Moritz Kulawik / moritz.kulawik@lu.ch / [[user:Moritz]]   * Moritz Kulawik / moritz.kulawik@lu.ch / [[user:Moritz]]
-  * Claire-Michelle Loock / claire-michelle.loock@ben-energy.com+  * Claire-Michelle Loock / claire-michelle.loock@ben-energy.com [[user:cloock]]
   * Urs Mändl / urs.maendli@energie360.ch   * Urs Mändl / urs.maendli@energie360.ch
-  * Derrick Oswald / derrick.oswald@9code.ch+  * Derrick Oswald / derrick.oswald@9code.ch / [[user:derrickoswald]]
   * Erwin Sägesser / erwin.saegesser@nis.ch / [[user:erwinsaegesser]]   * Erwin Sägesser / erwin.saegesser@nis.ch / [[user:erwinsaegesser]]
 +  * Nadim Schumann / nadim.schumann@qbis.ch
  
 ===== Links ===== ===== Links =====
  • project/hotornot.txt
  • Last modified: 2016/04/19 08:09
  • by eggenberger_afca.ch