編碼

The science of Neufast system

Our mission is to provide you and your candidates with engaging and highly accurate recruitment without bias. We ensure our scores are always valid, reliable, and fair by our deeply scientific, multi-layered AI-model.

Visual, Audio and Textual Based Comprehensive Analysis

Candidate’s apparent features, prosody features and semantic features are extracted from his/her videos based on computer vision, speech recognition and natural language processing techniques.

Visual channel for apparent feature extraction

Apparent features such as facial expression and gesture are implicitly extracted by computer vision technique.

cloud-computing.png

Audio channel for prosody feature extraction

Prosody features such as tonality, pace and rhythm are implicitly extracted by audio analysis technique

script.png

Textual channel for semantic feature extraction

The syntactic and semantic meaning of candidate’s spoken texts are extracted by natural language processing technique with contextual awareness

AI Model Architecture

Our AI model further analyzes these features in a comprehensive way with complex task-oriented adaptive weighting scheme to infer candidate’s Impression Score and Work Performance Score.

Training of AI Model

Visual, Audio and Textual channels

(Deep Learning Models)

Apparent

features

Prosody

features

Customized Regression

Impression / Competency Scores

Semantic

features

Internal Governance of Developing Fair AI Model

Neufast embraces good data ethics in operation and the development and use of AI. To ensure the fairness of AI model, the development process is under internal governance:

  • No manipulation of the training data collection leading to a biased model in favor of some certain group

  • No data preprocessing that changes the data distributions for different groups

​Data Preparation

  • All key aspects of the model building process are reviewed

  • Salient numerical results are copied into the sheet

  • All significant deviations from the standard model training process are well documented

Model Building &
Training

  • Adverse Impact Assessment is done to evaluate if our trained AI model complies with the UGESP's four-fifth rule* with respect to different groups in either: Demography, Educational background or other groups defined by clients

Model Testing

*Reference: Equal Employment Opportunity Commission, Civil Service Commission, et al. 1978. Uniform guidelines on employee selection procedures. Federal Register 43, 166 (1978), 38290–38315.

​Assessment of Impression performance

Neufast’s AI video assessment tool can assess candidate’s capability in making a positive impression on others through three perspectives:

Communication

Self-confidence

Positive emotions

​Assessment of Motivation

Neufast’s AI video assessment tool can identify how candidate is motivated to initiate work-related behavior.

Assessment of
Work Performance

Neufast’s competency model is built from cumulated studies on work performance. Candidates will be assessed through their task, contextual and adaptive performance.

Comprises job-specific behaviors which include accomplishing the role responsibilities and activities listed in in job description.

notepad.png
Task
performance

Job and Role Responsibilities

Leadership and Management Behaviors

Job and Role Responsibilities

Leadership and Management Behaviors

Job and Role Responsibilities

Leadership and Management Behaviors

Job and Role Responsibilities

Leadership and Management Behaviors

unity.png
Contextual performance

Comprises non-job specific behaviors that help maintain or improve the broader organizational, social or psychological environment necessary to facilitate task performance and achieving organizational goal accomplishments

Relationship and Communication

Comprises behaviors and attitude required to be flexible and be able to quickly adapt to dynamic work situations

corporate.png
Adaptive performance

Adaptation and Change

Reliability study

Our AI video assessment tool is highly reliable and accurate to our client’s internal rating. We analyzed the efficiency of our product by comparing our AI scores to HR (Client) internal rating: 

Cronbach’s Alpha > 0.7 (out of 1) for reliability,​

Positive Pearson correlation 0.3 - 0.6 (out of 1) at p<0.05 significant level for impression scores (including enthusiasm, self-confidence, and composure) and at competency-level

bar-chart.png