Pump and Dumps in the Bitcoin Era: Real Time Detection of Cryptocurrency Market Manipulations

Morgia, Massimo La; Mei, Alessandro; Sassi, Francesco; Stefa, Julinda

doi:10.1109/icccn49398.2020.9209660

Cited by 32 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kamps et al [14] conduct anomaly detection on the moving averages of price and trading volume data. La et al [15,16] improve this method by introducing much more fine-grained features, like market buy orders. Besides only based on market statistics data, Mirtaheri et al [20] take into account the statistics of tweets and users that mentioned cryptocurrency to make the detection.…”

Section: Coin Embedding Testmentioning

confidence: 99%

“…Besides only based on market statistics data, Mirtaheri et al [20] take into account the statistics of tweets and users that mentioned cryptocurrency to make the detection. Even though some of the approaches [15,16] argue they can achieve real-time response, the post-detection paradigm fails to meet the practical needs since the coin price can easily reach its peak in less than one minute after a P&D begins. Target Coin Prediction: Xu et al [26] firstly introduce this task and use a RF model to predict the target coin, treating P&Ds as isolated, unrelated events and not solve the cold-start problem.…”

Section: Coin Embedding Testmentioning

confidence: 99%

“…Figure 1: The $NAS pump-and-dump coordinated by the Telegram channel "Binance Trading Signals".As P&Ds occur frequently and attract more public attention, it becomes imperative to detect such fraudulent activities[13,27] and inform potentially susceptible investors before they become victims. Existing efforts[14][15][16]20] mainly fall into the category of P&D post-detection, which aims to detect whether a P&D has happened or is happening. However, we argue that this paradigm fails to meet the practical needs since the coin price can easily reach its peak in less than one minute after a P&D begins, thus leaving no time to alert investors.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump

Hu¹,

Zhang²,

Lu³

et al. 2022

Preprint

View full text Add to dashboard Cite

As the pump-and-dump schemes (P&Ds) proliferate in the cryptocurrency market, it becomes imperative to detect such fraudulent activities in advance, to inform potentially susceptible investors before they become victims.In this paper, we focus on the target coin prediction task, i.e., to predict the pump probability of all coins listed in the target exchange before a pump. We conduct a comprehensive study of the latest P&Ds, investigate 709 events organized in Telegram channels from Jan. 2019 to Jan. 2022, and unearth some abnormal yet interesting patterns of P&Ds. Empirical analysis demonstrates that pumped coins exhibit intra-channel homogeneity and inter-channel heterogeneity, which inspires us to develop a novel sequence-based neural network named SNN. Specifically, SNN encodes each channel's pump history as a sequence representation via a positional attention mechanism, which filters useful information and alleviates the noise introduced when the sequence length is long. We also identify and address the coin-side cold-start problem in a practical setting. Extensive experiments show a lift of 1.6% AUC and 41.0% Hit Ratio@3 brought by our method, making it well-suited for real-world application. As a side contribution, we release the source code of our entire data science pipeline on GitHub 1 , along with the dataset tailored for studying the latest P&Ds.

show abstract

Section: Coin Embedding Testmentioning

confidence: 99%

Section: Coin Embedding Testmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump

Hu¹,

Zhang²,

Lu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…al. [16] have observed how fraud is committed. Then, they are drawing attention to the low liquidity in the crypto money markets.…”

Section: Related Workmentioning

confidence: 99%

Manipulator Detection in Cryptocurrency Markets Based on Forecasting Anomalies

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For example, when inspecting visualizations of stock trading or other financial time-series [36], analysts can point to events that seem to match a specific pattern, such as episodes of "pump and dump" in crypto-currency markets. These are market manipulation events that consist of artificially inflating the price of an owned security (in this case a crypto-currency) and then selling it at a much higher price [21]. Figure 1 shows the hourly price for Vibe from September 9 to 11, 2018.…”

Section: Introductionmentioning

confidence: 99%

Finding Patterns in Visualized Data by Adding Redundant Visual Information

Eisler¹,

Meyer²

2022

Preprint

View full text Add to dashboard Cite

We present "PATRED", a technique that uses the addition of redundant information to facilitate the detection of specific, generally described patterns in line-charts during the visual exploration of the charts. We compared different versions of this technique, that differed in the way redundancy was added, using nine distance metrics (such as Euclidean, Pearson, Mutual Information and Jaccard) with judgments from data scientists which served as the "ground truth". Results were analyzed with correlations (R 2 ), F1 scores and Mutual Information with the average ranking by the data scientists. Some distance metrics consistently benefit from the addition of redundant information, while others are only enhanced for specific types of data perturbations. The results demonstrate the value of adding redundancy to improve the identification of patterns in time-series data during visual exploration.

show abstract

Pump and Dumps in the Bitcoin Era: Real Time Detection of Cryptocurrency Market Manipulations

Cited by 32 publications

References 12 publications

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump

Manipulator Detection in Cryptocurrency Markets Based on Forecasting Anomalies

Finding Patterns in Visualized Data by Adding Redundant Visual Information

Contact Info

Product

Resources

About