{"id":134894,"date":"2026-09-07T13:33:57","date_gmt":"2026-09-07T08:03:57","guid":{"rendered":"https:\/\/www.guvi.in\/blog\/?p=134894"},"modified":"2026-09-07T13:33:58","modified_gmt":"2026-09-07T08:03:58","slug":"ai-bias-mitigation-techniques","status":"publish","type":"post","link":"https:\/\/www.guvi.in\/blog\/ai-bias-mitigation-techniques\/","title":{"rendered":"AI Bias Mitigation Techniques: A Practical Guide"},"content":{"rendered":"\n<p>AI systems learn from data, and biased data can lead to biased predictions and decisions. <strong>AI Bias Mitigation<\/strong> involves identifying, measuring, and reducing unfair patterns throughout the machine learning lifecycle. From improving training data to evaluating model outputs, organizations can use multiple techniques to make AI systems more fair, reliable, and responsible. This guide explains practical <strong>AI Bias Mitigation<\/strong> techniques and how they can be applied to real-world machine learning workflows.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>TL;DR Summary<\/strong><\/h3>\n\n\n\n<ul>\n<li>AI bias can originate from data, models, or deployment.<\/li>\n\n\n\n<li>Bias should be assessed throughout the ML lifecycle.<\/li>\n\n\n\n<li>Better data can reduce biased model behavior.<\/li>\n\n\n\n<li>Fairness metrics help identify disparities.<\/li>\n\n\n\n<li>Regular monitoring is essential after deployment.<\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Direct Answer<\/strong><\/h4>\n\n\n\n<figure class=\"wp-block-table has-medium-font-size\"><table><tbody><tr><td><strong>AI Bias Mitigation<\/strong> involves identifying and reducing unfair patterns in AI systems through better data, model evaluation, fairness-aware training, and continuous monitoring. Techniques such as dataset balancing, bias testing, representative sampling, fairness constraints, and human review can help reduce discriminatory outcomes and make machine learning systems more reliable across different groups and use cases.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Why AI Bias Mitigation Matters<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1200\" height=\"707\" src=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20-1200x707.webp\" alt=\"Why AI Bias Mitigation Matters\" class=\"wp-image-134896\" srcset=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20-1200x707.webp 1200w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20-300x177.webp 300w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20-768x453.webp 768w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20-1536x905.webp 1536w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20-150x88.webp 150w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-20.webp 1634w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" title=\"\"><\/figure>\n\n\n\n<p>AI systems can influence decisions involving hiring, lending, healthcare, education, advertising, and other important areas. If biased patterns exist in training data or model behavior, they can be reproduced or amplified by the system.<\/p>\n\n\n\n<p>Effective bias mitigation helps support:<\/p>\n\n\n\n<ul>\n<li>Fairer predictions<\/li>\n\n\n\n<li>More representative datasets<\/li>\n\n\n\n<li>Better model reliability<\/li>\n\n\n\n<li>Responsible AI development<\/li>\n\n\n\n<li>Greater transparency<\/li>\n\n\n\n<li>Reduced discriminatory outcomes<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Is AI Bias?<\/strong><\/h2>\n\n\n\n<p><strong>AI <\/strong><a href=\"https:\/\/www.guvi.in\/blog\/bias-and-ethical-concerns-in-machine-learning\/\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>bias<\/strong><\/a> occurs when an AI system produces systematically unfair or unequal outcomes for certain individuals or groups.<\/p>\n\n\n\n<p>Bias can enter an AI system through several sources.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Biased Training Data<\/strong><\/h3>\n\n\n\n<p>Historical datasets may contain existing inequalities or underrepresent certain groups.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Sampling Bias<\/strong><\/h3>\n\n\n\n<p>A dataset may not accurately represent the population where the model will be used.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Labeling Bias<\/strong><\/h3>\n\n\n\n<p>Human annotators may introduce subjective or inconsistent judgments into training labels.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Algorithmic Bias<\/strong><\/h3>\n\n\n\n<p>Model design or optimization objectives can produce unequal outcomes.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Deployment Bias<\/strong><\/h3>\n\n\n\n<p>A model that performs well in one environment may behave unfairly when applied to a different population or context.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How to Identify AI Bias<\/strong><\/h2>\n\n\n\n<p>Before mitigating bias, teams need to measure where it exists.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Analyze Training Data<\/strong><\/h3>\n\n\n\n<p>Check whether important groups are adequately represented and whether historical patterns may introduce bias.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Compare Model Performance<\/strong><\/h3>\n\n\n\n<p>Evaluate model performance separately across relevant groups instead of relying only on overall accuracy.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Examine Prediction Outcomes<\/strong><\/h3>\n\n\n\n<p>Look for systematic differences in false positives, false negatives, approval rates, or other outcomes.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Conduct Fairness Audits<\/strong><\/h3>\n\n\n\n<p>Regular audits can help identify disparities that may not be visible through standard performance metrics.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Practical AI Bias Mitigation Techniques<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Improve Dataset Representation<\/strong><\/h3>\n\n\n\n<p>Use diverse and representative datasets to reduce underrepresentation.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Balance Training Data<\/strong><\/h3>\n\n\n\n<p>Where appropriate, address significant class or group imbalances before <a href=\"https:\/\/www.guvi.in\/blog\/ai-foundation-models\/\">model<\/a> training.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Review Labels<\/strong><\/h3>\n\n\n\n<p>Check whether annotation guidelines and labeling decisions introduce systematic bias.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Use Fairness Metrics<\/strong><\/h3>\n\n\n\n<p>Evaluate model outcomes using appropriate fairness measures alongside traditional performance metrics.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Apply Fairness-Aware Training<\/strong><\/h3>\n\n\n\n<p>Modify model training or optimization approaches when fairness requirements are part of the system&#8217;s objectives.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Human Oversight<\/strong><\/h3>\n\n\n\n<p>Use human review for high-impact decisions and cases where automated predictions require additional context.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>AI Bias Mitigation Across the ML Lifecycle<\/strong><\/h2>\n\n\n\n<p>Bias mitigation should not happen only after a model has been trained.<\/p>\n\n\n\n<p><strong>Data Collection \u2192 Labeling \u2192 Training \u2192 Evaluation \u2192 Deployment \u2192 Monitoring<\/strong><\/p>\n\n\n\n<p>At each stage, teams can evaluate whether the system is producing unexpected disparities and take corrective action where necessary.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Real-World Applications<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1200\" height=\"706\" src=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1-1200x706.webp\" alt=\"Real-World Applications\" class=\"wp-image-134897\" srcset=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1-1200x706.webp 1200w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1-300x177.webp 300w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1-768x452.webp 768w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1-1536x904.webp 1536w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1-150x88.webp 150w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Real-World-1-1.webp 1635w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" title=\"\"><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Hiring<\/strong><\/h3>\n\n\n\n<p>Evaluate whether automated screening systems produce systematically different outcomes across candidate groups.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Financial Services<\/strong><\/h3>\n\n\n\n<p>Monitor lending or credit models for potentially unfair differences in approval or risk outcomes.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Healthcare<\/strong><\/h3>\n\n\n\n<p>Evaluate AI systems across relevant patient populations to identify performance disparities.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Computer Vision<\/strong><\/h3>\n\n\n\n<p>Test recognition systems across diverse demographic and environmental conditions.<\/p>\n\n\n\n<div style=\"background-color: #099f4e; border: 3px solid #110053; border-radius: 12px; padding: 18px 22px; color: #FFFFFF; font-size: 18px; font-family: Montserrat, Helvetica, sans-serif; line-height: 1.6; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15); max-width: 750px;\"> \n  <strong style=\"font-size: 22px; color: #FFFFFF;\">\ud83d\udca1 Did You Know?<\/strong> \n  <br \/><br \/> \nDon&#8217;t rely on overall accuracy alone when evaluating an AI system for fairness. A model can achieve high overall accuracy while performing significantly worse for a particular group. Always examine performance across relevant groups and use fairness measures appropriate to the application.\n\n\n\n\n\n\n\n\n\n \n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Benefits of AI Bias Mitigation<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Fairer AI Systems<\/strong><\/h3>\n\n\n\n<p>Mitigation techniques can reduce systematic disparities in model outcomes.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Better Reliability<\/strong><\/h3>\n\n\n\n<p>Testing across different groups can reveal weaknesses that overall metrics hide.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Greater Trust<\/strong><\/h3>\n\n\n\n<p>Transparent evaluation and monitoring can improve confidence in AI systems.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Responsible Deployment<\/strong><\/h3>\n\n\n\n<p>Bias assessment helps organizations make more informed decisions about where and how AI should be used.<\/p>\n\n\n\n<p>Professionals interested in responsible AI, machine learning, and AI development can strengthen their expertise through <strong>HCL GUVI&#8217;s <\/strong><a href=\"https:\/\/www.guvi.in\/courses\/bundles\/artificial-intelligence-machine-learning\/?utm_source=blog&amp;utm_medium=hyperlink+&amp;utm_campaign=ai-bias-mitigation-techniques\" target=\"_blank\" data-type=\"link\" data-id=\"https:\/\/www.guvi.in\/courses\/bundles\/artificial-intelligence-machine-learning\/?utm_source=blog&amp;utm_medium=hyperlink+&amp;utm_campaign=ai-bias-mitigation-techniques\" rel=\"noreferrer noopener\"><strong>Artificial Intelligence and Machine Learning Course<\/strong><\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>When Should You Apply AI Bias Mitigation?<\/strong><\/h2>\n\n\n\n<p><strong>AI Bias Mitigation<\/strong> should be applied throughout the machine learning lifecycle, especially when AI systems influence decisions that can significantly affect people.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>High-Impact Decisions<\/strong><\/h3>\n\n\n\n<p>Use bias evaluation when AI supports decisions related to hiring, lending, healthcare, education, or other sensitive areas.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Diverse User Groups<\/strong><\/h3>\n\n\n\n<p>Evaluate models when they are expected to serve populations with different demographic, geographic, or behavioral characteristics.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Imbalanced Datasets<\/strong><\/h3>\n\n\n\n<p>Apply mitigation techniques when certain groups or classes are significantly underrepresented in training data.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Model Evaluation<\/strong><\/h3>\n\n\n\n<p>Check group-level performance before deployment instead of relying only on overall accuracy.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Production Monitoring<\/strong><\/h3>\n\n\n\n<p>Continue monitoring deployed models because changes in data or user populations can introduce new sources of bias.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Key Concepts to Remember<\/strong><\/h2>\n\n\n\n<ul>\n<li>Bias can originate from data, labeling, model design, or deployment.<\/li>\n\n\n\n<li>Representation matters when building training datasets.<\/li>\n\n\n\n<li>Overall accuracy does not guarantee fairness.<\/li>\n\n\n\n<li>Group-level performance can reveal hidden disparities.<\/li>\n\n\n\n<li>Human review can be valuable for high-impact decisions.<\/li>\n\n\n\n<li>Bias mitigation should continue after deployment.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>A Practical AI Bias Mitigation Workflow<\/strong><\/h2>\n\n\n\n<p>A structured approach can help teams identify and reduce bias.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>1. Identify Potential Sources of Bias<\/strong><\/h3>\n\n\n\n<p>Review data collection, sampling, labels, model objectives, and deployment conditions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>2. Analyze the Dataset<\/strong><\/h3>\n\n\n\n<p>Check representation, missing information, class imbalance, and historical patterns that could affect outcomes.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>3. Train the Model<\/strong><\/h3>\n\n\n\n<p>Build the model while considering relevant fairness requirements alongside predictive performance.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>4. Evaluate Group-Level Results<\/strong><\/h3>\n\n\n\n<p>Compare important performance and outcome metrics across relevant groups.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>5. Apply Mitigation Techniques<\/strong><\/h3>\n\n\n\n<p>Depending on the problem, improve the dataset, adjust training methods, or introduce additional safeguards.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>6. Validate Again<\/strong><\/h3>\n\n\n\n<p>Re-evaluate the model after mitigation to determine whether disparities have actually been reduced without creating unacceptable performance trade-offs.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>7. Monitor After Deployment<\/strong><\/h3>\n\n\n\n<p>Continue checking model behavior as real-world data and user populations change.<\/p>\n\n\n\n<p>The <strong>HCL GUVI&#8217;s <a href=\"https:\/\/www.guvi.in\/mlp\/genai-ebook\/?utm_source=blog&amp;utm_medium=hyperlink+&amp;utm_campaign=ai-bias-mitigation-techniques\" target=\"_blank\" rel=\"noreferrer noopener\">Artificial Intelligence eBook<\/a><\/strong> introduces the fundamentals of artificial intelligence, machine learning, generative AI, and intelligent automation. It helps learners build a broader understanding of AI technologies and responsible approaches to developing intelligent systems.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Best Practices<\/strong><\/h2>\n\n\n\n<ul>\n<li>Use representative and relevant training data.<\/li>\n\n\n\n<li>Document dataset and labeling decisions.<\/li>\n\n\n\n<li>Evaluate performance across relevant groups.<\/li>\n\n\n\n<li>Select fairness metrics appropriate to the use case.<\/li>\n\n\n\n<li>Keep fairness evaluation separate from overall accuracy.<\/li>\n\n\n\n<li>Include human oversight for high-impact applications.<\/li>\n\n\n\n<li>Monitor deployed systems for changing patterns.<\/li>\n\n\n\n<li>Reassess models when data or use cases change.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Conclusion<\/strong><\/h2>\n\n\n\n<p><strong>AI Bias Mitigation<\/strong> is an ongoing process rather than a single model-training step. By examining data, evaluating group-level outcomes, improving training approaches, and monitoring deployed systems, organizations can identify and reduce unfair patterns more effectively. A responsible approach combines fairness evaluation with model performance, human oversight, and continuous monitoring to build AI systems that are more reliable and appropriate for real-world use.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>FAQs<\/strong><\/h2>\n\n\n<div id=\"rank-math-faq\" class=\"rank-math-block\">\n<div class=\"rank-math-list \">\n<div id=\"faq-question-1787377515463\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>1. What is AI Bias Mitigation?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p><strong>AI Bias Mitigation<\/strong> refers to techniques used to identify, reduce, and monitor unfair patterns in AI systems throughout the machine learning lifecycle.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787377522999\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>2. Where can AI bias originate?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Bias can come from training data, sampling, labeling, model design, optimization objectives, or differences between development and deployment environments.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787377536888\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>3. Does high model accuracy mean an AI system is fair?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>No. A model can have high overall accuracy while performing differently across specific groups. Group-level evaluation is therefore important.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787377550259\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>4. How can biased training data be addressed?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Teams can improve representation, review sampling methods, examine historical patterns, and apply appropriate data-balancing or preprocessing techniques.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787377559835\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>5. Why are fairness metrics important?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Fairness metrics help teams identify differences in model outcomes or performance across relevant groups that may not be visible through overall accuracy.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787377569258\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>6. Is bias mitigation only needed before deployment?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>No. Models should also be monitored after deployment because changes in data, users, or operating conditions can introduce new disparities.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787377580294\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>7. Why is human oversight important?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Human oversight can provide additional context and review for high-impact decisions where automated predictions may have significant consequences for individuals.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>AI systems learn from data, and biased data can lead to biased predictions and decisions. AI Bias Mitigation involves identifying, measuring, and reducing unfair patterns throughout the machine learning lifecycle. From improving training data to evaluating model outputs, organizations can use multiple techniques to make AI systems more fair, reliable, and responsible. This guide explains [&hellip;]<\/p>\n","protected":false},"author":7,"featured_media":137264,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[933],"tags":[],"views":"22","authorinfo":{"name":"HCL GUVI","url":"https:\/\/www.guvi.in\/blog\/author\/guvipr\/"},"thumbnailURL":"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/AI-Bias-Mitigation-Techniques-A-Practical-Guidee-300x116.webp","_links":{"self":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/134894"}],"collection":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/comments?post=134894"}],"version-history":[{"count":3,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/134894\/revisions"}],"predecessor-version":[{"id":137610,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/134894\/revisions\/137610"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media\/137264"}],"wp:attachment":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media?parent=134894"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/categories?post=134894"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/tags?post=134894"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}