Similarity Model in Analyst
Target PI | PI 1 |
Created Date | Dec 10, 2022 |
Jira Epic | |
---|---|
Document Status | Draft |
Epic Owner | @Caleb Paul |
Stakeholder | @Ben Bradley |
Engineering Team(s) Involved | Analyst |
Customer/User Job-to-be-Done or Problem
When [user situation/context/mindset], I want to [user need/goal], so I can [expected result/outcome].
Occupation-Occupation
Due to the tight labor market, organizations are being forced to expand their search for talent beyond workers who exactly match the role they are looking to fill. It’s becoming more common to hire workers in adjacent roles and train them up to work in the required role.
As a TA Manager, whenever I make the decision to expand my search to a broader pool of talent, I want to know which occupations are closely adjacent or similar to the primary occupation that I’m searching for, so that I can easily expand my search without having to spend extra time researching it elsewhere and I can be confident in the occupations I chose to include because I’m trusting Lightcast data instead of my own research.
Skill-Occupation
The job description skills parser is popular among users (especially new users) who are having trouble classifying a job. Currently the parser takes in a job description and then outputs recommended skills and job titles to search for. The skills and titles are determined by how frequent they show up in job postings. With the new similarity model, we can now suggest occupations to search for based on multiple skills.
As a TA Recruiter, whenever I’m unsure about whether the occupation I chose accurately describes the job req I’m working on, I want Lightcast to recommend occupations to me based on the job description, so that I can be confident knowing that I’m searching by the right occupation and that my search results are accurate.
Occupation-Occupation
The Talent Supply by Compensation report uses ONET Compatibility scores to show occupations with similar or related skillsets. With the new Similarity Model, we can now perform the same task with higher accuracy and recency based on the skills on job postings.
As a Staffing AM, whenever I’m negotiating pay rates with clients, I want to utilize the most accurate and recent labor market data as I talk about talent supply by compensation, so that my clients trust the data that I present instead of being skeptical and I can be more confident in my negotiating.
Value to Customers & Users
In the JTBD framework, these are the “pains” and “gains” your solution will address. Other ways to think about it: What’s the rationale for doing this work? Why is it a high priority problem for your customers and how will our solution add value?
Users are forced to think on their own as they try to translate the idea of a job in their heads into an occupation name. When they can rely on Lightcast to make that translation for them, it increases their efficiency and confidence.
Users will be able to search by all SOC occupations in their Talent Supply by Comp report again (see below)
Value to Lightcast
Sometimes we do things for our own benefit. List those reasons here.
We’re seen as better advisors to our clients from within the product
Since Lightcast has updated to ONET-2019, some occupations lost their associated skills that they had previously, and ONET has to build up a new list of skills for the modified ONET. Software Developer (15-1252) for example is a code that changed with the latest ONET release, so it doesn’t yet have any associated skills. As a result, it is an occupation that you cannot search for in the Talent Supply by Comp report.
Target User Role/Client/Client Category
Who are we building this for?
All customers across BUs, but especially TA and Staffing users.
Delivery Mechanism
How will users receive the value?
Across nations and verticals, in every Analyst report that has an occupation search input (SOC, ONET, and LOT)
Talent Supply by Comp
Success Criteria & Metrics
How will you know you’ve completed the epic? How will you know if you’ve successfully addressed this problem? What usage goals do you have for these new features? How will you measure them?
When it is always possible to get recommended occupations based on the first occupation you search by or by the job description you enter
When you can search by Software Developer in Talent Supply by Comp
Increase total occupation searches by 10% over the course of 3 months
Aspects that are out of scope (of this phase)
What is explicitly not a part of this epic? List things that have been discussed but will not be included. Things you imagine in a phase 2, etc.
The release of the Similar Occupation tab in JPT (this was canceled)
Solution Description
Early UX (wireframes or mockups)
Non-Functional Attributes & Usage Projections
Consider performance characteristics, privacy/security implications, required copy translations (mostly surveys), mobile requirements, accessibility requirements
Must be able to add/remove occupations to/from the search bar when items are clicked on.
Dependencies
Is there any work that must precede this? Feature work? Ops work?
None.
Legal and Ethical Considerations
Just answer yes or no.
High-Level Rollout Strategies
Initial rollout to [internal employees|sales demos|1-2 specific beta customers|all customers]
If specific beta customers, will it be for a specific survey launch date or report availability date
How will this guide the rollout of individual stories in the epic?
The rollout strategy should be discussed with CS, Marketing, and Sales.
How long we would tolerate having a “partial rollout” -- rolled out to some customers but not all
Release to all and inform marketing, CS, and Sales early.
Risks
Focus on risks unique to this feature, not overall delivery/execution risks.
Not that I know of.
Open Questions
What are you still looking to resolve?
TBD
Complete with Engineering Teams
Effort Size Estimate |
---|
Estimated Costs
Direct Financial Costs
Are there direct costs that this feature entails? Dataset acquisition, server purchasing, software licenses, etc.?
Team Effort
Each team involved should give a general t-shirt size estimate of their work involved. As the epic proceeds, they can add a link to the Jira epic/issue associated with their portion of this work.
Team | Effort Estimate (T-shirt sizes) | Jira Link |
---|---|---|
|
|
|
|
|
|