A UK-based startup, working in the applied psychology and coaching sector, approached us for help with their personality profiling procedures. Our client, and hundreds just like them, use personality profiling to assist their own customers in turn with management issues, such as making accurate recruitment decisions and dealing with day to day ‘person-centric’ employee workplace concerns.
This particular business approached Fountech Solutions, in order to see if using Artificial Intelligence could improve their profiling accuracy and perhaps reduce costs.
Profilers tend to use the industry standard ‘Myers Briggs Profile’ (MBP) as a framework to quantify personality traits. It’s generally acknowledged that once a person’s MBP is accurately assessed, it does tend to be useful in various workplace scenarios. However, arriving at a truly genuine profile can be fraught with difficulty. MBP testing involves a time consuming, formal ‘exam’ style procedure under empirical conditions.
Qualified psychologists within our customer’s team were assigned to work with us. They outlined their usual problems:
Testing is often skewed with bias, despite existing strategies, because respondents regularly try to second-guess their answers.
Implicit personality profiling can belong-winded and sporadic because employees must take time away from their desks.
GDPR workplace legislation can be a legal minefield for psychology professionals.
A brand new approach was required. We created writing style analysis software, which assigned MB personality profiles from mapping the grammar, style and construction of sent emails, (always with the employee’s consent). The process was dynamic and hyper-efficient, because the AI autonomously improved its own ongoing accuracy.
This meant that HR departments and managers could constantly access up to date ‘background analyses’ of their employees’ profiles, enabling future behavioural insights.
In order for this software to become truly reliable, we needed to train the AI with ‘known’ data as a benchmark.
The concept was nothing to do with analysing the ‘meaning’ of words, it was about understanding the inter-relationship of alpha and special characters, certain strings of words, all interpreted as compositional behaviours by given personality types. Natural language analysis algorithms, vectorization and a careful weighting of sentence elements were all used to assess peoples’ writing styles.
To train the AI, at first, a marker of 60% accuracy was set. If the AI was ‘told’ by the human subject that its result was under that score, a further questionnaire was asked of the respondent. Then the accuracy was checked again, and the writing style analysis algorithms updated to correct mistakes in profile matching. Fairly quickly, this reinforcement learning process by the AI managed to achieve a much higher score from its human feedback.
It didn’t take long for the AI to become uncannily accurate, the control group expressing amazement at its proficiency. At that point, the algorithm ‘recipes’ were integrated into a commercially viable product.
We created an online gamified ‘fun’ MB profile test for our client to distribute via social media and amongst their friends and families. The initial samplecomprised of over 1000 people, who performed the test and were assigned an MB ‘type’.
They were then asked to feedback as to their opinion of the accuracy of the results (and also about the results of their consenting friends). The same people then allowed the AI access to their sent email messages, once assured that the process could not compromise their privacy to legal standards.
Once the AI had an accurate profile for a person, it matched their writing style in terms of word patterns, (poor) grammar, punctuation, certain vocabulary, word repetition, overuse of uppercase letters, emoticons and hundreds of other factors.
Our software was integrated by the development team into a solution branded for the client, to sell as a package to corporations that would integrate into their email system, CRM and HR / L&D framework.
Early predictions of success were exceeded, in fact, fiscally measurable efficiency and teamwork improvements were noted when the product was used by a corporate banking organisation. Our client told us that other projects appeared to be progressing smoothly, with improved KPI’s for their customers after a few months of the system’s inception.
The vCAIO will conduct a situational assessment to identify the needs of, and opportunities for, the organisation. They will provide a report outlining a gap analysis and the baseline from where to start defining the AI strategy going forward
Create a vision of where the organisation should be going
Set standards for strategy implementation through establishing the correct management structures and considering ethical issues
Make things happen by operating at the right level, knowing what to outsource and what to achieve in-house for optimum delivery
Build capacity in the organisation by recruiting the right talent and identifying appropriate vendors or consultants to solve key problems
Become the public face of the new technology, both internally and externally
Understanding your needs and identifying opportunity to exploit
Evaluate your data
Knowledge Gaps | Costs v Benefits | Your Competitors
Latest Industry Tech and how we can enhance it just for you
Our key recommendations and suggested next steps