{"id":7067,"date":"2026-03-23T23:05:37","date_gmt":"2026-03-23T23:05:37","guid":{"rendered":"https:\/\/www.wizbrand.com\/tutorials\/synthetic-control\/"},"modified":"2026-03-23T23:05:37","modified_gmt":"2026-03-23T23:05:37","slug":"synthetic-control","status":"publish","type":"post","link":"https:\/\/www.wizbrand.com\/tutorials\/synthetic-control\/","title":{"rendered":"Synthetic Control: What It Is, Key Features, Benefits, Use Cases, and How It Fits in Attribution"},"content":{"rendered":"\n

Synthetic Control is a causal measurement method that helps marketers answer a hard question in Conversion & Measurement<\/strong>: What would have happened if we hadn\u2019t run this campaign, changed this landing page, or launched this channel?<\/em> In real-world marketing, true randomized experiments aren\u2019t always possible due to budget, operational constraints, or platform limitations. Synthetic Control provides a disciplined way to estimate the \u201ccounterfactual\u201d outcome\u2014often the missing piece behind credible Attribution<\/strong>.<\/p>\n\n\n\n

Modern Conversion & Measurement<\/strong> programs increasingly prioritize incrementality (causal impact) over correlation. Synthetic Control matters because it can turn messy, observational performance data into decision-ready insights: how many conversions were truly incremental, what the lift was, and whether the result is likely to hold up under scrutiny.<\/p>\n\n\n\n

What Is Synthetic Control?<\/h2>\n\n\n\n

Synthetic Control<\/strong> is a causal inference technique that estimates the impact of an intervention (like a campaign launch or product change) by comparing the treated unit (the market, audience segment, or time series that received the intervention) to a synthetic<\/em> comparison group. That synthetic group is constructed as a weighted blend of similar untreated units\u2014designed to match the treated unit\u2019s behavior before the intervention.<\/p>\n\n\n\n

At its core, Synthetic Control creates a high-quality \u201cvirtual twin\u201d of what would have happened without the intervention, using historical patterns and comparable markets or segments. The business meaning is straightforward: it helps quantify incremental conversions<\/strong>, incremental revenue<\/strong>, and the true causal impact of marketing and product decisions.<\/p>\n\n\n\n

In Conversion & Measurement<\/strong>, Synthetic Control often shows up in geo-based testing, market rollouts, and situations where A\/B testing is infeasible. Inside Attribution<\/strong>, it\u2019s frequently used to validate, calibrate, or challenge channel crediting models by providing an independent estimate of lift.<\/p>\n\n\n\n

Why Synthetic Control Matters in Conversion & Measurement<\/h2>\n\n\n\n

Synthetic Control strengthens Conversion & Measurement<\/strong> in ways that everyday reporting cannot:<\/p>\n\n\n\n

    \n
  • Separates lift from noise:<\/strong> Many channels \u201clook good\u201d when you measure only clicks or last-touch outcomes. Synthetic Control focuses on causal impact, reducing misleading signals.<\/li>\n
  • Improves budget allocation:<\/strong> By estimating incremental return, it helps shift spend toward what truly drives conversions rather than what merely captures demand.<\/li>\n
  • Enables credible measurement without perfect experiments:<\/strong> When you can\u2019t randomize users, you can often still build a convincing counterfactual using markets, stores, or segments.<\/li>\n
  • Supports defensible decision-making:<\/strong> Executives and finance teams respond better to measurement approaches that explicitly address the \u201cwhat would have happened anyway?\u201d question.<\/li>\n<\/ul>\n\n\n\n

    As Attribution<\/strong> becomes harder due to privacy constraints and reduced cross-site tracking, Synthetic Control becomes more valuable as a method that can work with aggregated or region-level outcomes\u2014especially when paired with strong governance and careful design.<\/p>\n\n\n\n

    How Synthetic Control Works<\/h2>\n\n\n\n

    Synthetic Control is both conceptual and procedural. In practice, it follows a clear workflow:<\/p>\n\n\n\n

      \n
    1. \n

      Input \/ Trigger (Define the intervention and unit)<\/strong>\n – Choose the \u201ctreated\u201d unit: a region, market, store cluster, audience cohort, or sometimes a product surface.\n – Define the intervention: a campaign, pricing change, creative launch, channel expansion, or site experience change.\n – Identify outcome measures relevant to Conversion & Measurement<\/strong>: conversions, revenue, trials, leads, retention, or qualified pipeline.<\/p>\n<\/li>\n

    2. \n

      Analysis \/ Processing (Build the synthetic baseline)<\/strong>\n – Select a donor pool of untreated units that did not receive the intervention.\n – Use pre-intervention data to find weights for donor units so their weighted combination closely matches the treated unit\u2019s pre-period trend.\n – Validate pre-period fit (the synthetic should track the treated unit closely before launch).<\/p>\n<\/li>\n

    3. \n

      Execution \/ Application (Estimate causal impact)<\/strong>\n – Compare treated vs. synthetic outcomes after the intervention.\n – The gap between actual treated performance and synthetic baseline is the estimated incremental effect.<\/p>\n<\/li>\n

    4. \n

      Output \/ Outcome (Interpretation for Attribution and decisions)<\/strong>\n – Translate lift into business terms: incremental conversions, incremental revenue, cost per incremental conversion, incremental ROAS.\n – Use uncertainty checks (placebo tests, sensitivity analysis) to judge confidence.\n – Feed results back into Attribution<\/strong> strategy: calibrate channel credit, refine MMM assumptions, or guide experimentation roadmaps.<\/p>\n<\/li>\n<\/ol>\n\n\n\n

      Key Components of Synthetic Control<\/h2>\n\n\n\n

      A robust Synthetic Control setup typically includes:<\/p>\n\n\n\n

      Data inputs<\/h3>\n\n\n\n
        \n
      • Historical time series for outcomes (conversions, revenue, retention)<\/li>\n
      • Marketing inputs (spend, impressions, reach, channel mix)<\/li>\n
      • Context variables (seasonality, promotions, holidays, macro effects, pricing)<\/li>\n
      • Eligibility and exposure definitions (what qualifies a unit as treated vs. untreated)<\/li>\n<\/ul>\n\n\n\n

        Processes and governance<\/h3>\n\n\n\n
          \n
        • Clear experiment-like design: pre-period length, post-period length, and launch date integrity<\/li>\n
        • Donor pool rules: avoid units indirectly affected by the intervention<\/li>\n
        • Documentation: assumptions, exclusions, and known confounders<\/li>\n
        • Cross-functional review: marketing, analytics, finance, and sometimes legal\/privacy<\/li>\n<\/ul>\n\n\n\n

          Statistical checks<\/h3>\n\n\n\n
            \n
          • Pre-period fit diagnostics<\/li>\n
          • Placebo or falsification tests (apply \u201cfake\u201d treatments to donor units)<\/li>\n
          • Sensitivity analysis (how results change when units are added\/removed)<\/li>\n<\/ul>\n\n\n\n

            Metrics and reporting<\/h3>\n\n\n\n
              \n
            • Incremental lift estimates with uncertainty<\/li>\n
            • Decision thresholds for scaling, stopping, or iterating<\/li>\n
            • A repeatable readout format for Conversion & Measurement<\/strong> stakeholders<\/li>\n<\/ul>\n\n\n\n

              Types of Synthetic Control<\/h2>\n\n\n\n

              Synthetic Control has a \u201cclassic\u201d form, but in marketing practice the most useful distinctions are contextual:<\/p>\n\n\n\n

              1) Geo-based Synthetic Control (market-level)<\/h3>\n\n\n\n

              Common for brand campaigns, offline media, retail rollouts, and region-targeted digital spend. This is a major workhorse in Conversion & Measurement<\/strong> because geo units are naturally separable and outcomes can be aggregated reliably.<\/p>\n\n\n\n

              2) Segment- or cohort-based Synthetic Control<\/h3>\n\n\n\n

              Used when geography isn\u2019t the right unit, such as customer cohorts, product categories, or partner groups\u2014provided you can find a credible donor pool that remains untreated.<\/p>\n\n\n\n

              3) Single treated unit vs. multiple treated units<\/h3>\n\n\n\n
                \n
              • Single treated unit:<\/strong> one market (e.g., a pilot city) vs. synthetic built from other cities.<\/li>\n
              • Multiple treated units:<\/strong> several treated markets; analysis may pool effects or estimate each unit\u2019s impact separately.<\/li>\n<\/ul>\n\n\n\n

                4) Regularized \/ augmented approaches (practical enhancements)<\/h3>\n\n\n\n

                In real datasets, perfect pre-period matching is hard. Many teams use variants that add regularization, covariates, or bias correction to improve stability and interpretability. The principle remains the same: construct a counterfactual using weighted combinations rather than a simple average.<\/p>\n\n\n\n

                Real-World Examples of Synthetic Control<\/h2>\n\n\n\n

                Example 1: Measuring incremental lift from a regional paid media push<\/h3>\n\n\n\n

                A company increases spend in three metro areas for six weeks to promote a new product line. Standard Attribution<\/strong> reports show strong last-touch performance, but leadership wants incremental impact.<\/p>\n\n\n\n

                  \n
                • Treated units: the three metros<\/li>\n
                • Donor pool: similar metros with no spend change<\/li>\n
                • Outcome: incremental purchases and revenue<\/li>\n
                • Result: Synthetic Control estimates that only a portion of observed conversions were incremental, leading to a revised budget plan and improved Conversion & Measurement<\/strong> discipline.<\/li>\n<\/ul>\n\n\n\n

                  Example 2: Evaluating a landing page overhaul where user-level randomization isn\u2019t feasible<\/h3>\n\n\n\n

                  A regulated business can\u2019t easily run user-level A\/B tests across all traffic due to compliance review cycles. They roll out a new experience to a defined customer segment first.<\/p>\n\n\n\n

                    \n
                  • Treated unit: the rollout segment<\/li>\n
                  • Donor pool: comparable segments not yet migrated<\/li>\n
                  • Outcome: qualified lead submissions and downstream conversion rate<\/li>\n
                  • Result: Synthetic Control isolates the lift from the redesign and prevents over-crediting paid channels in Attribution<\/strong> (since traffic mix changed during rollout).<\/li>\n<\/ul>\n\n\n\n

                    Example 3: Quantifying the impact of expanding into a new channel<\/h3>\n\n\n\n

                    A B2B team launches a new upper-funnel channel for one quarter. Pipeline increases, but seasonality and a parallel sales promotion complicate Conversion & Measurement<\/strong>.<\/p>\n\n\n\n

                      \n
                    • Treated unit: regions where the channel was activated<\/li>\n
                    • Donor pool: regions without activation<\/li>\n
                    • Outcome: marketing-qualified leads and sales-qualified pipeline<\/li>\n
                    • Result: Synthetic Control supports a measured scale-up and informs Attribution<\/strong> weighting for upper-funnel influence.<\/li>\n<\/ul>\n\n\n\n

                      Benefits of Using Synthetic Control<\/h2>\n\n\n\n

                      Synthetic Control delivers practical advantages for Conversion & Measurement<\/strong> and Attribution<\/strong>:<\/p>\n\n\n\n

                        \n
                      • More credible incrementality estimates:<\/strong> Especially when randomized experiments aren\u2019t possible.<\/li>\n
                      • Better spend efficiency:<\/strong> Helps reduce investment in channels that harvest existing demand rather than create new conversions.<\/li>\n
                      • Improved planning and forecasting:<\/strong> A stronger causal baseline improves confidence in scenario planning.<\/li>\n
                      • Cross-team alignment:<\/strong> Provides a shared \u201csource of truth\u201d for lift that marketing, finance, and product can debate constructively.<\/li>\n
                      • Resilience to tracking limitations:<\/strong> Often works with aggregated outcomes, supporting privacy-forward Conversion & Measurement<\/strong> approaches.<\/li>\n<\/ul>\n\n\n\n

                        Challenges of Synthetic Control<\/h2>\n\n\n\n

                        Synthetic Control is powerful, but not automatic:<\/p>\n\n\n\n

                          \n
                        • Donor pool contamination:<\/strong> If \u201ccontrol\u201d units are indirectly exposed (spillover from national media, shared audiences, supply constraints), estimates can be biased.<\/li>\n
                        • Poor pre-period fit:<\/strong> If the synthetic baseline can\u2019t match historical patterns, causal conclusions become fragile.<\/li>\n
                        • Time-varying confounders:<\/strong> External shocks (pricing changes, competitor moves, outages) can distort results.<\/li>\n
                        • Small sample size at the unit level:<\/strong> Too few markets or too little historical data reduces stability.<\/li>\n
                        • Interpretation risk in Attribution:<\/strong> A lift estimate doesn\u2019t automatically assign credit across channels; it indicates net impact of an intervention package unless designed more granularly.<\/li>\n<\/ul>\n\n\n\n

                          In Conversion & Measurement<\/strong>, the biggest failure mode is treating Synthetic Control like a reporting trick rather than a quasi-experimental design that needs careful assumptions.<\/p>\n\n\n\n

                          Best Practices for Synthetic Control<\/h2>\n\n\n\n

                          To make Synthetic Control dependable and repeatable:<\/p>\n\n\n\n

                            \n
                          1. \n

                            Design like an experiment<\/strong>\n – Lock the intervention date, inclusion rules, and success metrics before analyzing outcomes.\n – Use a sufficiently long pre-period to capture seasonality and demand cycles.<\/p>\n<\/li>\n

                          2. \n

                            Build a clean donor pool<\/strong>\n – Exclude units with overlapping exposure, major operational differences, or separate promotions.\n – Document why each unit qualifies as untreated.<\/p>\n<\/li>\n

                          3. \n

                            Validate pre-period fit<\/strong>\n – If the synthetic baseline doesn\u2019t closely track the treated unit historically, reconsider the unit, donor pool, or covariates.<\/p>\n<\/li>\n

                          4. \n

                            Run falsification and sensitivity checks<\/strong>\n – Placebo tests (fake interventions) help detect whether your method \u201cfinds lift\u201d where none should exist.\n – Remove one donor unit at a time to see whether results hinge on a single comparator.<\/p>\n<\/li>\n

                          5. \n

                            Translate results into decisions<\/strong>\n – Tie outcomes to Conversion & Measurement<\/strong> actions: scale, pause, iterate creative, adjust targeting, or change budget allocation.\n – Use results to inform Attribution<\/strong> governance rather than replacing it.<\/p>\n<\/li>\n<\/ol>\n\n\n\n

                            Tools Used for Synthetic Control<\/h2>\n\n\n\n

                            Synthetic Control is methodology-first, but it depends on a capable measurement stack:<\/p>\n\n\n\n

                              \n
                            • Analytics tools:<\/strong> To define conversions, cohorts, funnels, and ensure metric consistency across treated and donor units.<\/li>\n
                            • Data warehouses \/ data pipelines:<\/strong> To assemble reliable time series, join spend and exposure data, and enforce consistent definitions.<\/li>\n
                            • Experimentation and geo-testing workflow systems:<\/strong> To manage market selection, holdouts, calendars, and pre\/post windows in Conversion & Measurement<\/strong> programs.<\/li>\n
                            • Reporting dashboards:<\/strong> To communicate lift, uncertainty, and decision thresholds to stakeholders.<\/li>\n
                            • CRM systems and revenue reporting:<\/strong> Essential when outcomes are downstream (pipeline, revenue) and when Attribution<\/strong> needs alignment with sales reality.<\/li>\n
                            • Statistical computing environments:<\/strong> Where modeling, weighting, placebo tests, and reproducibility practices live.<\/li>\n<\/ul>\n\n\n\n

                              The most important \u201ctool\u201d is operational: a repeatable process that ensures every Synthetic Control analysis can be audited and reproduced.<\/p>\n\n\n\n

                              Metrics Related to Synthetic Control<\/h2>\n\n\n\n

                              When Synthetic Control is used for Conversion & Measurement<\/strong>, the most common metrics include:<\/p>\n\n\n\n

                                \n
                              • Incremental conversions \/ incremental revenue:<\/strong> The core causal outcome (treated minus synthetic).<\/li>\n
                              • Lift percentage:<\/strong> Incremental change relative to the synthetic baseline.<\/li>\n
                              • Cost per incremental conversion (CPIC):<\/strong> Spend divided by incremental conversions.<\/li>\n
                              • Incremental ROAS \/ ROI:<\/strong> Incremental revenue (or margin) divided by incremental cost.<\/li>\n
                              • Pre-period fit quality:<\/strong> Often tracked via error measures comparing treated vs. synthetic before the intervention.<\/li>\n
                              • Uncertainty indicators:<\/strong> Confidence intervals where applicable, plus placebo distribution comparisons.<\/li>\n
                              • Heterogeneous effects:<\/strong> Lift by market size, audience composition, or funnel stage to guide optimization and Attribution<\/strong> refinement.<\/li>\n<\/ul>\n\n\n\n

                                Future Trends of Synthetic Control<\/h2>\n\n\n\n

                                Several trends are shaping how Synthetic Control evolves within Conversion & Measurement<\/strong>:<\/p>\n\n\n\n

                                  \n
                                • Privacy-driven aggregation:<\/strong> As user-level tracking becomes more restricted, Synthetic Control methods that work with aggregated time series and geo units become more central.<\/li>\n
                                • Automation of experiment design:<\/strong> More teams are systematizing market selection, donor pool rules, and monitoring to run Synthetic Control-like studies continuously.<\/li>\n
                                • AI-assisted covariate selection and anomaly detection:<\/strong> AI can help detect confounders (e.g., outages, pricing changes) and recommend robustness checks, but human governance remains critical.<\/li>\n
                                • Closer integration with Attribution frameworks:<\/strong> Expect more \u201chybrid\u201d measurement where Synthetic Control provides ground-truth lift estimates used to calibrate MMM and to sanity-check multi-touch Attribution<\/strong> outputs.<\/li>\n
                                • Faster decision loops:<\/strong> Organizations will push Synthetic Control beyond quarterly studies toward monthly or even campaign-level learning, especially for geo and retail media.<\/li>\n<\/ul>\n\n\n\n

                                  Synthetic Control vs Related Terms<\/h2>\n\n\n\n

                                  Synthetic Control vs A\/B testing<\/h3>\n\n\n\n
                                    \n
                                  • A\/B testing<\/strong> randomizes exposure and is the gold standard for causality at the user level.<\/li>\n
                                  • Synthetic Control<\/strong> is used when randomization isn\u2019t feasible; it builds a counterfactual from comparable units.\nIn Conversion & Measurement<\/strong>, A\/B tests are preferred when possible; Synthetic Control is often the next-best causal tool.<\/li>\n<\/ul>\n\n\n\n

                                    Synthetic Control vs Difference-in-Differences (DiD)<\/h3>\n\n\n\n
                                      \n
                                    • Difference-in-Differences<\/strong> compares changes over time between treated and control groups, typically assuming parallel trends.<\/li>\n
                                    • Synthetic Control<\/strong> explicitly constructs a weighted control to better match pre-trends, often improving credibility when simple controls are not comparable.\nFor Attribution<\/strong> discussions, Synthetic Control can be more persuasive when stakeholders question whether controls are truly \u201clike for like.\u201d<\/li>\n<\/ul>\n\n\n\n

                                      Synthetic Control vs Marketing Mix Modeling (MMM)<\/h3>\n\n\n\n
                                        \n
                                      • MMM<\/strong> estimates channel contributions over time, often at an aggregate level, and supports budget optimization.<\/li>\n
                                      • Synthetic Control<\/strong> estimates the causal impact of a specific intervention or launch.\nThey complement each other in Conversion & Measurement<\/strong>: Synthetic Control can validate MMM assumptions or provide lift benchmarks to calibrate Attribution<\/strong> and ROI estimates.<\/li>\n<\/ul>\n\n\n\n

                                        Who Should Learn Synthetic Control<\/h2>\n\n\n\n

                                        Synthetic Control is worth learning for:<\/p>\n\n\n\n

                                          \n
                                        • Marketers:<\/strong> To understand incrementality, evaluate campaigns honestly, and avoid optimizing to misleading Attribution<\/strong> signals.<\/li>\n
                                        • Analysts and data scientists:<\/strong> To add a rigorous causal tool to the Conversion & Measurement<\/strong> toolkit and improve stakeholder trust.<\/li>\n
                                        • Agencies:<\/strong> To provide defensible performance measurement, especially for brand and omni-channel programs.<\/li>\n
                                        • Business owners and founders:<\/strong> To make better investment decisions and distinguish true growth drivers from correlation.<\/li>\n
                                        • Developers and data engineers:<\/strong> To build the pipelines, unit definitions, and reproducible systems needed to operationalize Synthetic Control at scale.<\/li>\n<\/ul>\n\n\n\n

                                          Summary of Synthetic Control<\/h2>\n\n\n\n

                                          Synthetic Control is a causal measurement method that constructs a weighted \u201csynthetic\u201d baseline to estimate what outcomes would have been without an intervention. It matters because modern Conversion & Measurement<\/strong> requires incrementality, not just correlation. Used well, Synthetic Control strengthens Attribution<\/strong> by providing lift-based evidence that can validate channel impact, guide budget allocation, and improve confidence in marketing decisions\u2014especially when randomized testing is impractical.<\/p>\n\n\n\n

                                          Frequently Asked Questions (FAQ)<\/h2>\n\n\n\n

                                          1) What is Synthetic Control used for in marketing?<\/h3>\n\n\n\n

                                          Synthetic Control is used to estimate the incremental impact of campaigns, rollouts, and channel changes by comparing actual outcomes to a synthetic counterfactual baseline built from similar untreated units.<\/p>\n\n\n\n

                                          2) Is Synthetic Control part of Attribution or Conversion & Measurement?<\/h3>\n\n\n\n

                                          It\u2019s primarily a Conversion & Measurement<\/strong> method for causal impact, but it strongly influences Attribution<\/strong> by validating whether reported conversions reflect true lift.<\/p>\n\n\n\n

                                          3) When should I use Synthetic Control instead of an A\/B test?<\/h3>\n\n\n\n

                                          Use Synthetic Control when user-level randomization isn\u2019t feasible, when changes are launched by market\/region, or when the intervention affects broad exposure that\u2019s hard to randomize cleanly.<\/p>\n\n\n\n

                                          4) What makes a good donor pool for Synthetic Control?<\/h3>\n\n\n\n

                                          A good donor pool includes untreated units that resemble the treated unit historically, are not exposed to spillover effects, and have stable measurement definitions across the full time range.<\/p>\n\n\n\n

                                          5) How do I know if my Synthetic Control result is trustworthy?<\/h3>\n\n\n\n

                                          Trust increases when pre-period fit is strong, placebo tests don\u2019t show frequent \u201cfake lift,\u201d results are robust to donor pool changes, and known confounders are documented and addressed.<\/p>\n\n\n\n

                                          6) Can Synthetic Control tell me which channel deserves credit in Attribution?<\/h3>\n\n\n\n

                                          Not by itself. Synthetic Control estimates the net impact of an intervention bundle unless you design separate treatments. It\u2019s best used to calibrate or sanity-check Attribution<\/strong> models rather than replace them.<\/p>\n\n\n\n

                                          7) What outcomes work best for Synthetic Control in Conversion & Measurement?<\/h3>\n\n\n\n

                                          Aggregated, stable outcomes like purchases, revenue, trials, qualified leads, or store sales typically work well\u2014especially when measured consistently across treated and untreated units over time.<\/p>\n","protected":false},"excerpt":{"rendered":"

                                          Synthetic Control is a causal measurement method that helps marketers answer a hard question in **Conversion & Measurement**: *What would have happened if we hadn\u2019t run this campaign, changed this landing page, or launched this channel?* In real-world marketing, true randomized experiments aren\u2019t always possible due to budget, operational constraints, or platform limitations. Synthetic Control provides a disciplined way to estimate the \u201ccounterfactual\u201d outcome\u2014often the missing piece behind credible **Attribution**.<\/p>\n","protected":false},"author":10235,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1888],"tags":[],"class_list":["post-7067","post","type-post","status-publish","format-standard","hentry","category-attribution"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/posts\/7067","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/users\/10235"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/comments?post=7067"}],"version-history":[{"count":0,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/posts\/7067\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/media?parent=7067"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/categories?post=7067"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wizbrand.com\/tutorials\/wp-json\/wp\/v2\/tags?post=7067"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}