Sales Call Classification on Industry Vertical
Engineering, IT, Mathematics and Statistics
- This internship is able to cover project costs for domestic students only.
- The Industry Partner has implemented appropriate preparations to comply with Federal and State Government requirements regarding COVID-19 safety.
ABOUT THE INDUSTRY PARTNER
Delacon develops leading telecommunication technology solutions and specialise in telecommunications and cloud-based SaaS (Software as a Services). They are an industry leader in call tracking and are the only Google Analytics Certified Partner in the world that does Call Tracking. Delacon currently identify online marketing channels and AdWords keywords that yield high value phone sales then optimise and refine campaigns to deliver more high value phone calls. Delacon can then automatically capture data into a client CRM to see the user journey from online to phone sale. One such method of data capture uses a third-party transcribing voice-to-text module.
Delacon developed a speech analytics module, which is able to analyse the transcribed call data (already speech converted to data) and produce reporting of:
- Customer sentiment
- Conversation keyword trends
Delacon need a PhD intern to help drive and lead Predictive Analysis of calls to classify whether a sale has happened or not in the conversation on industry vertical (e.g. telecommunication, insurance, automobile etc.). The intern will be working with Delacon‘s software development team collaboratively. The intern will have access to real commercial big data; join a team with experimental mindsets with commercial and human centred design focus. This will include experience in both technical and business entrepreneurship.
WHAT’S IN IT FOR YOU?
Opportunity to work with the AI and design team, and work with live data sets and gain valuable first-hand experience in a fast-moving commercial organisation. Working with the head of IT and other specialised staff transferring skills. It will lead to intern potential employment or develop skills and experience to take to new employer.
RESEARCH TO BE CONDUCTED
- Researching latest academic literature / thinking on conversation text machine learning classification
- Identify and manage data collection and prepare required data for model development
- Research, design and implement a classifier system to align with automatic identification of whether actual sale occurred or not during the conversation on industry verticals
- Conduct mathematical model simulation and test prediction accuracy (i.e. collection and set up training dataset and validation dataset)
- Implement the solution in Delacon’s SaaS platform
SKILLS WISH LIST
- Computer Science, Machine Learning, Natural Language Processing, Text mining
- Java, SQL, Python and related packages/libraries for machine learning and text mining
- Research, design, implement and evaluate novel algorithms in the field of predictive analytics
- Experience designing analytic or algorithmic solutions to problems
The aim is to develop a software module that can
- Identify if a sale has happened in the call or not, on industry vertical
- A software module integrated in the Delacon SAAS platform which will analyse the transcription text (audio converted to text using third-party speech-to-text conversion service) and report whether a sale has happened or not in the call conversation. Since the conversation pattern is different in different industries, the software might work on industry vertical level such as telecommunication, insurance, health etc.
The intern will receive $3,000 per month of the internship, usually in the form of scholarship payments.
It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
CONNECT WITH APR.INTERN