NavBoost: How Google Uses Click Behavior to Re-Rank Search Results

What is NavBoost?

NavBoost is Google's click-based re-ranking system. It observes what users do after a Google search — which results they click, how long they stay, and whether they return to the search page — and uses this behavioral data to adjust rankings. It is not a content analysis system; it does not read web pages. Instead, it treats user behavior as a proxy for content quality: if users consistently click a result and stay, that result probably satisfied their need.

The system was confirmed as one of Google's "most important" ranking signals during the US Department of Justice antitrust trial in 2023, when Google's Vice President of Search, Pandu Nayak, testified under oath that click data plays a central role in search ranking. This was the first official confirmation from a senior Google executive that click behavior is used as a direct ranking signal — contradicting years of public statements from Google that downplayed the role of click-through rate.

The click signals: goodClicks, badClicks, lastLongestClicks

The Google API leak of May 2024 revealed the specific fields NavBoost uses to classify clicks. Three field names appear in the leaked documentation: goodClicks, badClicks, and lastLongestClicks. These are not raw click counts — they are classified outcomes of user interactions.

goodClicks represent clicks where the user appeared satisfied — they clicked a result and did not return to the search page, or spent a meaningful amount of time on the destination. badClicks represent the opposite: the user clicked through but quickly bounced back to the search results, indicating the page did not meet their need. lastLongestClicks is the strongest signal of all: it captures the last, longest click in a search session, marking the result that finally satisfied the user's need.

The distinction between good and bad clicks is not binary — it involves a squashing function that weights clicks based on dwell time, click position, and other factors. The exact thresholds are hand-crafted by Google engineers, not machine-learned, which means they can be analyzed, adjusted, and debugged — a characteristic that the DOJ trial revealed is a deliberate architectural choice at Google.

The 13-month aggregation window

NavBoost does not work in real time — it aggregates click behavior over a rolling 13-month window. This means a page's NavBoost score reflects a full year of user interaction data, weighted toward more recent behavior. The long window makes NavBoost resistant to short-term manipulation: a few days of artificial clicks will not meaningfully move a score built on months of genuine user behavior.

However, the DOJ trial also revealed a companion system called "Instant Glue" that operates on a 24-hour log of user interaction data. Instant Glue provides near-real-time freshness boosts for queries where timeliness matters — a separate mechanism from the 13-month NavBoost aggregation. The two systems complement each other: NavBoost provides the stable, long-term quality signal; Instant Glue provides the short-term freshness signal.

The DOJ trial: what was revealed under oath

The US v. Google antitrust trial (September–November 2023) produced the most significant disclosures about Google's ranking systems in the company's history. For years, Google maintained a carefully cultivated ambiguity about the role of user behavior signals in ranking. When SEO practitioners observed that click-through rate appeared to affect rankings, Google could respond with technically accurate but misleading statements about how CTR was "not a ranking factor." The trial made such ambiguity untenable.

Pandu Nayak, Google's VP of Search, confirmed under oath that click data is used as a direct ranking signal. He described a system that tracks which results users click on, how long they stay, and whether they return to the search results page. This testimony directly contradicted prior public statements from Google employees, including former head of web spam Matt Cutts, who had repeatedly stated that click-through rate was too noisy to serve as a reliable ranking signal.

A later exhibit, PXR0356, documented a February 2025 call with Google engineer Hyung-Jin Kim, who confirmed that NavBoost was his second signal project at Google, that he has many patents related to it, and that he spent many years developing it. This exhibit provided the direct link between the leaked system name "NavBoost" and a specific Google engineer with patent filings.

Patent analysis: three Stufe 1 patents

Three US patents directly name Hyung-Jin Kim as inventor and describe systems for modifying search result ranking based on implicit user feedback — the mechanism NavBoost implements. All three are classified as Stufe 1 (the strongest evidence bridge) because the inventor is confirmed as the NavBoost developer via DOJ Exhibit PXR0356.

US10229166B1, granted March 2019, describes "modifying search result ranking based on implicit user feedback" — the core NavBoost mechanism. US8661029B1, granted February 2014, is the original patent in the family, filed in 2006. US8938463B1, granted January 2015, extends the system to correct for presentation bias (the tendency of users to click higher-ranked results regardless of quality).

A fourth patent, US9092510B1, was reviewed and discarded. It describes a temporal element of user feedback but has different inventors (Stets, Paskin) with no Kim connection — Stufe 3, functional similarity only. This illustrates the source discipline that distinguishes this reference from typical SEO commentary: a patent that sounds relevant is not included unless the evidence chain is strong enough.

NavBoost in the ranking architecture

The DOJ trial revealed that Google's ranking system ultimately boils down to two fundamental top-level signals: Quality (Q*) and Popularity (P*). NavBoost feeds into the Popularity signal, which measures how widely visited and well-linked a page is. Quality (Q*) is the other pillar — it assesses the trustworthiness and authority of a website, heavily influenced by PageRank.

Within this architecture, NavBoost is part of the ABC signals — Anchors (links), Body (content terms), and Clicks (user behavior) — that form the base topicality score (T*). These three signals together determine how relevant a document is to a query. NavBoost's specific contribution is the click component: it provides the behavioral verification that a document actually satisfies users for a given query.

NavBoost feeds into GLUE (System 3), which combines NavBoost with Chrome visit data to create a unified user behavior signal. The relationship is hierarchical: NavBoost captures search-driven clicks; GLUE adds direct-visit data from the Chrome browser; together they form a comprehensive picture of user satisfaction.

Implications for SEO practitioners

NavBoost cannot be directly manipulated — it reflects genuine user satisfaction aggregated over 13 months. This is by design: Google wants a signal that is resistant to gaming. But the implications for SEO are profound.

First, title and meta description optimization takes on new significance. These elements determine whether users click, and whether the resulting page meets the expectation set by the snippet. A page that ranks well but generates badClicks — because its snippet overpromises or its content underdelivers — will see its ranking degrade over time as NavBoost accumulates negative behavioral data.

Second, the concept of 'pogo-sticking' (clicking a result, bouncing back, clicking another result) is confirmed as a real negative signal. NavBoost's badClicks classification directly captures this pattern. Pages that consistently fail to satisfy users — even if they rank well initially through other signals — will be demoted.

Third, the long aggregation window means that SEO changes take time to show their full effect. A content improvement made today will not fully influence NavBoost for months. This is why Google's ranking changes often appear gradual rather than sudden — the behavioral signal needs time to accumulate.

Finally, the DOJ trial's confirmation that almost all Google signals are hand-crafted (not ML-based) means that the ranking system is ultimately understandable by human engineers. This is a significant finding for the SEO industry: it means that systematic observation, hypothesis testing, and evidence-based analysis can uncover how the system works — which is exactly what this reference aims to do.