Paper: arXiv 2504.15790

Authors: Mahya Karbalaii

Abstract

Building on our prior threshold-based analysis of six months of Poloniex trading data, we have extended both the temporal span and granularity of our study by incorporating minute-level OHLCV records for 1021 tokens around each confirmed pump-and-dump event. First, we algorithmically identify the accumulation phase, marking the initial and final insider volume spikes, and observe that 70% of pre-event volume transacts within one hour of the pump announcement. Second, we compute conservative lower bounds on insider profits under both a single-point liquidation at 70% of peak and a tranche-based strategy (selling 20% at 50%, 30% at 60%, and 50% at 80% of peak), yielding median returns above 100% and upper-quartile returns exceeding 2000%. Third, by unfolding the full pump structure and integrating social-media verification (e.g., Telegram announcements), we confirm numerous additional events that eluded our initial model. We also categorize schemes into “pre-accumulation” versus “on-the-spot” archetypes-insights that sharpen detection algorithms, inform risk assessments, and underpin actionable strategies for real-time market-integrity enforcement.

Complexity vs Empirical Score

  • Math Complexity: 2.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; no out-of-sample test; see penalty flags)
  • Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 8.0)

Why this score: The paper employs relatively simple statistical measures (thresholds, averages, distributions) and algorithmic logic rather than advanced stochastic calculus or heavy derivations, but it is heavily data-driven with minute-level OHLCV records, multi-event analysis, and concrete profit quantification, making it backtest-ready and implementation-heavy.

Research Flowchart

  flowchart TD
  A["Research Goal: Quantify Pump-and-Dump Dynamics"] --> B["Data Input<br>1021 Tokens: Minute-Level OHLCV"]
  B --> C["Methodology: Event Study<br>Identify Pumps via Volume Spikes"]
  C --> D["Computational Process A<br>Estimate Insider Profits"]
  C --> E["Computational Process B<br>Identify Accumulation Phase<br>Verify via Social Media"]
  D --> F["Key Findings"]
  E --> F
  subgraph F ["Outcomes"]
      F1["Median Returns > 100%"]
      F2["High Returns via Tranche Selling<br>(Sell at 50%, 60%, 80% of Peak)"]
      F3["70% of Pre-Event Volume in 1 Hour"]
      F4["Categorized: Pre-accumulation vs On-the-spot"]
  end

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes an algorithmic method to identify insider accumulation phases around pump‑and‑dump events and to compute conservative lower‑bound profit estimates for insiders.

Source sentence
First, we algorithmically identify the accumulation phase, marking the initial and final insider volume spikes, and observe that 70% of pre-event volume transacts within one hour of the pump announcement.

Assumes 4

  • The accumulation phase most likely occurs within four days preceding the target date. data
    Source sentence
    On these grounds, we posit that the accumulation phase most likely occurs within four days preceding the Target Date.
  • Insiders liquidate at a fixed fraction of the observed peak high price (70% for single‑point, or staged fractions for tranche). model
    Source sentence
    Single-Point Liquidation: Sell full volume V at 0.70 × H, where H is the observed peak high price.
  • Minute‑level OHLCV data are sufficient to estimate purchase‑price proxies and liquidation outcomes. data
    Source sentence
    given our reliance on minute-level data, we define two conservative unloading scenarios below to produce lower-bound profit estimates.
  • Social‑media announcements (e.g., Telegram) reliably confirm organized pump events. other
    Source sentence
    integrating social-media verification (e.g., Telegram announcements), we confirm numerous additional events that eluded our initial model.

Data

Backtest sample: Poloniex cryptocurrency tokens · crypto · intraday

  • Poloniex minute‑level OHLCV data · Poloniex market-prices public
    15 August 2024 to 15 February 2025 · 1021 tokens with flagged pump‑and‑dump events
    Source sentence
    We obtained our dataset from Poloniex’s public API [9], comprising 1,101 trading pairs over the six-month period from 15 August 2024 to 15 February 2025.

Costs

Not modeled A trading or execution result is reported without costs.

Finds 5

  • Approximately 70% of pre‑event trading volume occurs within one hour of the pump announcement. statistical
    Source sentence
    observe that 70% of pre-event volume transacts within one hour of the pump announcement.
  • Median insider returns exceed 100% and upper‑quartile returns exceed 2000% under the proposed liquidation scenarios. performance
    Source sentence
    yielding median returns above 100% and upper-quartile returns exceeding 2000%.
  • Accumulation phase durations have a mean of 2,160.8 minutes, with a heavy right‑tail indicating some events span several days. statistical
    Source sentence
    ... Figure 4 shows the full distribution of accumulation spans, highlighting the heavy right-tail of events with very extended pre-pump positioning.
  • Profit estimation scenarios produce average absolute profits ranging from $507.73 to $617.27 and median percentage profits from 92.02% to 126.70%. performance
    Source sentence
    Table 3: Profit estimation results for each scenario (A–D).
  • Integrating social‑media verification uncovers additional pump events that were missed by the initial threshold model. other
    Source sentence
    by unfolding the full pump structure and integrating social-media verification (e.g., Telegram announcements), we confirm numerous additional events that eluded our initial model.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 29 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (30)

  1. Cryptocurrency pump and dump schemes: Quantification and detection. (2019)
  2. To the moon: Analyzing cryptocurrency pump-and-dump schemes. (2018)
  3. The anatomy of a pump-and-dump scheme. (2019)
  4. The 2024 Crypto Crime Report. (2024)
  5. Guidance for a Risk-Based Approach to Virtual Assets and Virtual Asset Service Providers. (2019)
  6. Securities Exchange Act of 1934. (1934)
  7. Cryptocurrency Pump and Dump Schemes: Quantification and Detection (2023)
  8. Cryptocurrency Pump and Dump Schemes: Quantification and Detection (2019)
and 22 more
  1. Hybrid Cryptocurrency Pump and Dump Detection (2020)
  2. Machine Learning-Based Detection of Pump-and-Dump Schemes in Real-Time (2024) — link
  3. Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump (2023)
  4. Pump-and-Dump Schemes in Financial Markets: Evidence and Analysis (2008)
  5. Pump, Dump, and then What? The Long-Term Impact of Cryptocurrency Pump-and-Dump Schemes (2023) — link
  6. Fraud, Regulation and Enforcement: An International Perspective on Market Manipulation (2015)
  7. Information Asymmetry and Fraudulent Trading: Evidence from Pump-and-Dump Schemes (2010)
  8. Exploratory Data Analysis (EDA) for Banking and Finance: Unveiling Insights and Patterns (2024)
  9. Major Issues in High-Frequency Financial Data Analysis: A Survey of Solutions (2025)
  10. A Historical Analysis of Pump and Dump Schemes and Market Manipulation (1999)
  11. Price Manipulation in the Bitcoin Ecosystem (2018)
  12. Candlestick Patterns and their Role in Market Data Analysis (2012)
  13. Deep Learning for Anomaly Detection: A Survey (2019) — link
  14. Unsupervised Anomaly Detection in Time Series: Challenges and Opportunities (2020)
  15. Anomaly Detection: A Survey (2009)
  16. Conditional Anomaly Detection in Complex Data: Methods and Applications (2019)
  17. Detecting Crypto Pump-and-Dump Schemes: A Thresholding-Based Approach to Handling Market Noise — → 2503.08692
  18. Monetary Evolution: How Societies Shaped Money from Antiquity to Cryptocurrencies (2025) — link
  19. The Doge of Wall Street: Analysis and Detection of Pump and Dump Cryptocurrency Manipulations (2023)
  20. https://api-docs.poloniex.com/spot/api/public/market-data
  21. Efficient Capital Markets: A Review of Theory and Empirical Work (1970)
  22. Japanese Candlestick Charting Techniques (1991)

1 of 30 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.