Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/adamouization/neural-network-ticketing-routing-agent

:ticket: Ticketing-routing agent using neural networks trained to submit new tickets based on pre-determined optimal parameters.

https://github.com/adamouization/neural-network-ticketing-routing-agent

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (15.3%) to scientific vocabulary

Keywords

ai artificial-intelligence artificial-neural-networks decision-tree heatmap matplotlib multilayer-perceptron multilayer-perceptron-network neural-network numpy pandas scikit-learn scikitlearn-machine-learning ticketing-system
Last synced: 5 months ago · JSON representation

Repository

:ticket: Ticketing-routing agent using neural networks trained to submit new tickets based on pre-determined optimal parameters.

Basic Info
  • Host: GitHub
  • Owner: Adamouization
  • License: gpl-3.0
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 13.4 MB
Statistics
  • Stars: 2
  • Watchers: 3
  • Forks: 0
  • Open Issues: 3
  • Releases: 0
Topics
ai artificial-intelligence artificial-neural-networks decision-tree heatmap matplotlib multilayer-perceptron multilayer-perceptron-network neural-network numpy pandas scikit-learn scikitlearn-machine-learning ticketing-system
Created about 6 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Neural-Network-Ticketing-Routing-Agent HitCount GitHub license

Neural-Network-Ticketing-Routing-Agent is a neural-network-based ticketing routing agent. The agent is trained and tested with a multilayer feedforward neural network, and interacts with a user through a command-line interface, allowing the agent to ask the user questions to create a new ticket, with the capacity to make early predictions and retrain if the user comes up with a new combination of answers for a ticket. The optimal parameters are found with a grid search algorithm that tests 12,600 unique combinations of parameters (over 5 runs for even 80%/20% data splits), narrowing the neural network down to 14 optimal combinations. The agent is developed in Python 3.7 using the Scikit-Learn, NumPy, Pandas and Matplotlib libraries.

The report, which includes a summary of features implemented, design & implementation decisions (data encoding and training/testing split), evaluation (training/testing result visualisation in plots and heatmaps, grid search algorithm for determining optimal hyperparameters) and testing sections, can be read here.

Usage

Clone the repository (or download the zipped project): $ git clone https://github.com/Adamouization/Neural-Network-Ticketing-Routing-Agent

Create a virtual environment for the project and activate it:

virtualenv ~/Environments/Neural-Network-Ticketing-Routing-Agent source Neural-Network-Ticketing-Routing-Agent/bin/activate

Once you have the virtualenv activated and set up, cd into the project directory and install the requirements needed to run the app:

pip install -r requirements.txt

You can now run the app: python A4Main.py [-h] -a AGENT -c CSV [-g] [-d]

where:

  • AGENT is the type of agent to run: [Bas, Int, Adv]:
    • Bas: Train and test the neural network with the optimal parameters, or run the Grid Search algorithm to determine the optimal parameters.
    • Int: CLI text-based application to submit a new ticket and predict to which response team it should go.
    • Adv: Train and test a decision tree classifier.
  • CSV is the CSV file containing the data used to train/test the data.
  • -g: flag set to run the grid search algorithm.
  • -d: flag set to enter debug mode, printing more statements to the command line.
  • -h: flag for help on how to use the agent (prints instructions on the command line).

Examples: * python A4Main.py -a Bas -c tickets -d to train/test the neural network. * python A4Main.py -a Bas -c tickets -g to run the grid search algorithm. * python A4Main.py -a Int -c tickets to submit a new ticket through the CLI text-based interface. * python A4Main.py -a Adv -c tickets to train/test the decision tree. * python A4Main.py -h for help on how to run the agent.

Contact

Owner

  • Name: Adam Jaamour
  • Login: Adamouization
  • Kind: user
  • Location: United Kingdom
  • Company: @NewDayTechnology

💻 Data Scientist @NewDayTechnology 🧠 MSc AI @ Uni of St Andrews 📓 BSc Computer Science @ Uni of Bath 💼 Former SWE @ Scuderia Alpha Tauri F1 Team

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 0
  • Total pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 3
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • dependabot[bot] (3)
Top Labels
Issue Labels
Pull Request Labels
dependencies (3)

Dependencies

requirements.txt pypi
  • cycler ==0.10.0
  • futures ==3.1.1
  • joblib ==0.14.1
  • kiwisolver ==1.1.0
  • matplotlib ==3.1.2
  • numpy ==1.17.4
  • pandas ==0.25.3
  • pyparsing ==2.4.5
  • pyspin ==1.1.1
  • python-dateutil ==2.8.1
  • pytz ==2019.3
  • scikit-learn ==0.22
  • scipy ==1.3.3
  • seaborn ==0.9.0
  • six ==1.13.0