AU2021100597A4 - Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector - Google Patents
Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector Download PDFInfo
- Publication number
- AU2021100597A4 AU2021100597A4 AU2021100597A AU2021100597A AU2021100597A4 AU 2021100597 A4 AU2021100597 A4 AU 2021100597A4 AU 2021100597 A AU2021100597 A AU 2021100597A AU 2021100597 A AU2021100597 A AU 2021100597A AU 2021100597 A4 AU2021100597 A4 AU 2021100597A4
- Authority
- AU
- Australia
- Prior art keywords
- machine learning
- employment
- information
- skill
- ites
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063118—Staff planning in a project environment
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Employment and Skill Gap Identification Technique using Machine Learning
for ITES Sector
ABSTRACT
The achievement of operational workers in every company based on the technical skills they
possess, and these skills sets decide the productivity of the organization in various market
circumstances. As such, in today's competitive economy, it is impossible for companies to retain
profitability due to a major large skills deficit in the labour force. Because skill gap identification
offers significant details to workers such that management can concentrate on the expertise needed
to boost efficiency. This innovative proposal promotes the machine learning technique called
Random forest algorithm to identify the employment skill gaps between the employees in IT
enabled services. The analytical tools can be used for further refinement process and generates the
reports of employees regarding skill gaps to the higher officials in the ITES sector.
1
Description
Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector
Description
Field of the Invention:
In the industry and technological field, the concept Artificial Intelligence (AI) is also employed as an overarching terminology to relate to autonomous computers, applications and applications with reasoning or problem-solving capability. This involves the potential of machines to interpret natural language to associate with human beings, render projections depending on information to achieve observations, analyze the physical environment to operate a car modulate brain computational models to recognize artifacts or read text, and so on. Recent decades, the crucial aspect that perhaps the learning technologies have not achieved the expected outcomes is that they could have typically been deployed despite adequate awareness about where capabilities holes reside. This dilemma has becoming much further complicated with the proliferation of the socioeconomic corporation. The proposed invention provides a new mechanism to predict the employment and gap analysis using machine learning techniques like regression techniques.
Background of the invention:
According to Dhillon, the recruitment of staff influences the loyalty of consumers as the performance of the organization is dramatically harmed. In general, consumer concerns escalate while the turnover rate actively engaged and the resulting impact could be seen on the competitiveness and competitiveness of the organization Furthermore, the company would not be sufficient to preserve its strategic position in the industry. Employee retention is thus essential to assure the long-term development and performance of India's IT industry as a whole.
According to Jain the several organizations through countries have acknowledged that learning is an operational goal instead of a reactive solution which can be employed as a mechanism for progress and as a help to give an organization a sustainable privilege. The bulk of the organizations, thus, develop a consistent development program and are professionally integrated with the business philosophy instead of existing incidental to global operations. If the global economy progresses, preparation for emigrants is also underscored. The preparation and success of expats has been shown to be strongly correlated.
Fan et al., suggests the predictive approaches which incorporate employee historical data could be simpler and more reliable, because knowledge from all workers can be processed. The experience of workers and their success within the organization will include administrators and HR teams with information into their decision to leave the company. Prediction models that research the record archiving of workers, their success and the level of involvement or actions inside the company may thus be created. Usually, logistic regression, market basket statistical analysis or back spreading structures have been implemented to forecast performance, however struggle from a scarcity of validity of the process.
Sikaroudi et al sought to alleviate the issue of financial and time-related losses of the company as a consequence of the attrition of workers by creating a prediction model. It is feasible to evaluate employee performance by studying trends in their corporate and professional records. Based on statistics from the automobile components manufacturer, predictive models based on supervised machine learning techniques, multilayer perceptron, probabilistic neural network, SVM, classification and regression tree, K-nearest neighbour, naive Bayes, random forest, Apriori and CN2 algorithms were evaluated for validity, time for computation and user-friendly techniques. The outcomes demonstrated that the naive Bayes and the random forest had the maximum precision, whereas the naive Bayes was the most user-friendly method. Conversely, decision trees were the better frameworks in terms of time, precision and sociability.
Joel revealed that the primary adaptive consideration of superiors to subordinates is also correlated with improved success scores, and with other observations including such enhanced halo, decreased efficiency, improved organizational interactions, and a disincentive to discipline bad results.
In accordance with Longenecker, organizations are examined frequently spend less time and energy on organizational preparation and offer a valuable outline of opportunity to cover the gap in professional knowledge by performance. Highly experienced administrators of constantly evolving organizations have been surveyed for their expertise in professional development. The quality review has shown the most widely mentioned reasons why companies struggle to prepare their employees appropriately. Outcomes suggest that organisations are reluctant to prepare employees adequately for a myriad of factors.
In attempt to assess the importance of employee traits and operational factors, Heiat validated two supervised machine learning approaches to forecast employee performance. Both artificial neural networks and decision trees were conditioned on IBM Watson Analytics Population turnover results, where the regression function showed the significance of employee decades in the business and staff working extra shifts for both designs. While the ANN-based approach revealed a precision of 85.33%, the tree-based decision model was just 80.89% reliable. Consequently, the analysis endured from an inconsistency to resolve the ambient noise issue typically seen in every effective human resources results.
In the employee aspect of the analysis is the credentials that the employee maintains, and must satisfy the criteria to fulfil all the duties, roles and collaborate of the job necessary. In the collaborative works of Wilson, et al. in 2012, intelligence is characterized as data and details gained by an individual via training or qualifications; information reflects the amount of knowledge and Knowledge specifically implemented to the success of a mission. Skills are described as a physical, verbal or mental capacity to do a good job; skills are the product of a trained process. Skill is characterized as the presence of means to accomplish an operation or a process; ability is a measurable action to accomplish an operation or a project.
Objects of the Invention:
• The main objective is to develop the machine learning model to recognize the skill gaps in the sophisticated labour force, Companies would leverage of a proactive methodology to data processing and intellectual capacity. • The second objective is to assess the employee's expertise, assignments and training process, machine learning techniques may forecast whether abilities the employee might be focusing on to better promote the organization in the coming years. • Another objective is to develop Smart Al which can dynamically learn from knowledge by employing non-technical domain specialists to develop these skills and knowledge into predictable and reliable perspectives.
Summary of the Invention:
The skills gap is the discrepancy among the strategic objectives and the skills actually held by the employee within this task. Although several frameworks have been developed over time to resolve the complexities of the challenge, neither of them offers a systematic structure to explicitly define the specified skills and credentials of the staff and then determine the rate of resemblance. The assessment of skill gaps can be carried out by paper-based tests and accompanying conversations. Conversely, if an assessment needs to be carried out through a vast number of workers, there will be an immense pressure on management and administration. As a result, several companies adopt skill management tools.
The skill set including surveys, feedbacks, profiles and scorecards of individual employees is feed as input into the framework and preprocessing mechanisms are employed to remove the irrelevant information from the data collection. Feature selection is the method of choosing a subset of features that will be employed to build and train the system. This is the most significant procedure of machine learning, since it can impact the entire performance of the algorithm. Only certain factors that are most suitable for representing the answer parameter have been chosen in this method, whereas other parameters are discarded. Until evaluating the functionality, the data attributes were analyzed and any non-numeric parameters were translated to a quantitative form. The class 'Label Encoder' was employed converting non-numeric details into quantitative values and specifying weights for classification process.
Random forest is a framework consisting up of several decision trees. In preparation, each tree in a random forest trains from a random selection of datasets. Samples are taken with substitution, such as bootstrapping, which ensures that certain observations are being used several times in a single tree. The theory is that by training each tree on diagnostic experiments, while each tree will have a large dimensionality with regard to a specific collection of training effectiveness, collectively, the whole forest would have a lower complexity, but not at the expense of raising the bias. At the testing phase, the forecasting is done by an average of the decisions of each decision tree.
Detailed Description of the Invention:
Figure 1: The architecture of Employment and skills gap identification technique using machine learning
Figure 2: Random Forest architecture. Figure 3: R programming Analytical tool
Detailed Description of the Invention: Figure 1 explains the overall methodology to identify the employment and skill analysis gap technique using random forest mechanism. The skill set is composed of various features which is collected as surveys, feedbacks and profiles. The preprocessing mechanism is used to remove the irrelevant information. Feature selection is the method of choosing a subset of features that will be employed to build and train the system. This is the most significant procedure of machine learning, since it can impact the entire performance of the algorithm. Only certain factors that are most suitable for representing the answer parameter have been chosen in this method, whereas other parameters are discarded. The selected features are fed into the random forest classifier to classify the features. The classified information is further stored in the cloud storage. The analytical tools like R programming are used to analyze the stored information and generates the accurate results about individual employee performance and their skill gap analysis to the organization's ITES sector for further process.
Figure 2 demonstrates the architecture of Random forest algorithm. Random forest is a framework consisting up of several decision trees. In preparation, each tree in a random forest trains from a random selection of datasets. Samples are taken with substitution, such as bootstrapping, which ensures that certain observations are being used several times in a single tree. The theory is that by training each tree on diagnostic experiments, while each tree will have a large dimensionality with regard to a specific collection of training effectiveness, collectively, the whole forest would have a lower complexity, but not at the expense of raising the bias. At the testing phase, the forecasting is done by an average of the decisions of each decision tree.
Figure 3 explains the analytical tools processing. R is the main data analysis platform composed of a large range of algorithms for data storage, sorting, interpretation and high-end mathematical visualization. R also incorporated universal mathematical approaches like mean, median, distribution, covariance, regression, non-linear mixed effects, GLM, and GAM. R programming language functions can navigate all fields of process compared and integrate inferential statistics to draw such hypotheses that are critical for organizations.
Claims (7)
1. Employment and skill gaps identification technique consists of Data collection Data pre-processing Feature selection Random forest algorithm Cloud storage Data Analytical tools
2. According to claim, the information of individual employees is collected from various departments of the organization. The information such as feedbacks, surveys, profiles and personal information are gathered from various sources.
3. Claim 1 includes the pre-processing technique. Data pre- processing is among the most critical aspects of the data analysis process. Outcomes from data gathering or some other methodology can yield important and practical effects only if the accuracy of the datasets is preserved. Information gathered from HR databases is pre-processed by streamlining and encoding. Later, missed variables and deviations were tested. As far as the anomalies are concerned, the standard deviation analysis revealed no noticeable regression coefficients in the results, and thus the information was legally permitted for more process information.
4. Followed by claim 3, the feature selection process is employed for selecting the features from the skill sets. Feature selection strategy is utilized for reducing the feature space of the collected data and reducing the computational complexity. This is the most significant procedure of machine learning, since it can impact the entire performance of the algorithm. Only certain factors that are most suitable for representing the answer parameter have been chosen in this method, whereas other parameters are discarded.
5. The claim 1 also includes the random forest algorithm for further classification. Random forest algorithm gathers the features from the previous steps and classifies according to the class labels.
6. The cloud storage like Amazon web service, IBM cloud storage are used to store the processed information with high efficiency and security.
7. The data analytical tool like R programming analytical tool is proposed to analyze the processed information and generates the final reports which includes the skills gap and individual performance and provides to the Information Technology enables services (ITES) sector.
Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector
Drawings 2021100597
Figure 1: The architecture of Employment and skills gap identification technique using machine learning.
Figure 2: Random Forest architecture.
Figure 3: R programming Analytical tool
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021100597A AU2021100597A4 (en) | 2021-01-31 | 2021-01-31 | Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021100597A AU2021100597A4 (en) | 2021-01-31 | 2021-01-31 | Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021100597A4 true AU2021100597A4 (en) | 2021-04-15 |
Family
ID=75397113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021100597A Ceased AU2021100597A4 (en) | 2021-01-31 | 2021-01-31 | Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021100597A4 (en) |
-
2021
- 2021-01-31 AU AU2021100597A patent/AU2021100597A4/en not_active Ceased
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kaya et al. | Impact of RPA technologies on accounting systems | |
Mangla et al. | Critical success factors for reverse logistics in Indian industries: a structural model | |
Kotu et al. | Predictive analytics and data mining: concepts and practice with rapidminer | |
Abbady et al. | Big data governance, dynamic capability and decision-making effectiveness: Fuzzy sets approach | |
Met et al. | Transformation of business model in finance sector with artificial intelligence and robotic process automation | |
Kuzey et al. | An investigation of the factors influencing cost system functionality using decision trees, support vector machines and logistic regression | |
Dwivedi et al. | A two-phase approach to efficiently support product recovery systems in a circular economy context | |
Farahani et al. | Opportunities and challenges of applying artificial intelligence in the financial sectors and startups during the coronavirus outbreak | |
Kandepu | IBM FileNet P8: Evolving Traditional ECM Workflows with AI and Intelligent Automation | |
Bhardwaj et al. | Analysis and prediction of stock market movements using machine learning | |
AU2021100597A4 (en) | Employment and Skill Gap Identification Technique using Machine Learning for ITES Sector | |
Folorunso et al. | Data mining as a technique for knowledge management in business process redesign | |
Quan et al. | Human Resource Analytics on Data Science Employment Based on Specialized Skill Sets with Salary Prediction | |
Abushammala et al. | Transforming into smart business: The role of artificial intelligence | |
Jithitikulchai | Labor skills, economic returns, and automatability in Thailand | |
Citybabu et al. | Lean six sigma 4.0–a framework and review for lean six sigma practices in the digital era | |
Lahlou et al. | Business Process Reengineering in Agile Manufacturing–A Mixed Method Research | |
Popara et al. | Application of digital tools, data analytics and machine learning in internal audit | |
Ghosh et al. | Panic Selling Analysis in Stock Market | |
Chen et al. | Displacement or Augmentation? The Effects of AI on Workforce Dynamics and Firm Value | |
Dhanalakshmi et al. | Understanding Employee Attrition–An Organizational Change Perspective–using Predictive Analysis Techniques | |
Wijnands | Explaining black box decision-making: adopting explainable artificial intelligence in credit risk prediction for p2p lending | |
Akil et al. | A Synthesis on Machine Learning for Credit Scoring: A Technical Guide | |
Van Dam | Predicting Employee Attrition | |
Basha et al. | Exploring Machine Learning Models to Predict the Diamond Price: A Data Mining Utility Using Weka |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |