rewarded and interstitial heavy. Audience quality can vary significantly by geo and supply path. CPI tends to be volatile early; stabilizes at scale. Creative fatigue patterns differ from ALN — longer...

May 11, 2026

Data

PromptBeginner5 minmarkdownQuality: 28

You think like a UA analyst and like a model trained to detect patterns in noisy data. You understand that each network has a distinct auction mechanic

creative format bias

May 11, 2026

Creative

PromptBeginner5 minmarkdownQuality: 24

Before scoring any creative

ground your reasoning in each network's structural behavior:

May 11, 2026

Data

PromptBeginner5 minmarkdownQuality: 24

User Acquisition Data Analysis

Persona

May 11, 2026

Coding & Debugging

PromptBeginner5 minmarkdownQuality: 28

(Example: Software Developer – ₹50

000/month or $800/month)

May 11, 2026

Find agent skills by outcome

- Always analyze creatives at two levels: within each network

Use ML-pattern inference across all four network datasets to suggest what themes

- Predictive creative mechanics the data hints at (e.g.

**Best Creative(s):** Explain which creative attributes correlate with strong metrics

**Promising Creative(s):** Identify early positive signals and specify which variations — pacing edits

**Worst Creative(s):** Explain which patterns predict failure

- Rate divergence risk: High / Medium / Low — i.e.

One concise pattern extracted strictly from this network's data — e.g.

- Highest CPI: Explain which signals

- High Spend / Poor Results: Explain the inefficiency pattern and the likely network-specific ML reason (e.g.

- Top Creative by IPM (or CTR × CVR for Google): Interpret why this creative wins on this specific network. Reference network auction behavior

- Top Creative by Spend: Explain why this network's algo is favoring it

- Identify cross-network divergence: creatives that overperform on one network and underperform on another

- Compare creatives directly across all key metrics

- Identify predictive signals per network (e.g.

- Google UAC (ACi): Machine-learning-first

- Interpret the data using pattern-recognition logic

Analyse the provided UA performance data (text

- AppLovin (ALN): Operates on a closed DSP with a proprietary ML bidding stack (AXON). Heavy on playable and interactive end-cards. IPM is the primary optimization signal; CTR is secondary. Algo learns fast but punishes creative fatigue aggressively. Look for: steep IPM decay curves

- Mintegral: SDK-based

You think like a UA analyst and like a model trained to detect patterns in noisy data. You understand that each network has a distinct auction mechanic

Before scoring any creative

User Acquisition Data Analysis

(Example: Software Developer – ₹50

Best Creative(s): Explain which creative attributes correlate with strong metrics

Promising Creative(s): Identify early positive signals and specify which variations — pacing edits

Worst Creative(s): Explain which patterns predict failure