FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items

Yu Che Tsai; Chih Yao Chen; Shao Lun Ma; Pei Chi Wang; You Jia Chen; Yu Chieh Chang; Cheng Te Li

doi:10.1145/3298689.3346968

FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items

Yu Che Tsai, Chih Yao Chen, Shao Lun Ma, Pei Chi Wang, You Jia Chen, Yu Chieh Chang, Cheng Te Li

Institute of Data Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

15 Citations (Scopus)

Abstract

Financial technology (FinTech) draws much attention in these years, with the advances of machine learning and deep learning. In this work, given historical time series of stock prices of companies, we aim at forecasting upcoming anomalous fnancial items, i.e., abrupt soaring or diving stocks, in fnancial time series, and recommending the corresponding stocks to support fnancial operations. We propose a novel joint convolutional and recurrent neural network model, Financial Event Neural Network (FineNet), to forecast and recommend anomalous stocks. Experiments conducted on the time series of stock prices of 300 well-known companies exhibit the promising performance of FineNet in terms of precision and recall. We build FineNet as a Web platform for live demonstration.

Original language	English
Title of host publication	RecSys 2019 - 13th ACM Conference on Recommender Systems
Publisher	Association for Computing Machinery, Inc
Pages	536-537
Number of pages	2
ISBN (Electronic)	9781450362436
DOIs	https://doi.org/10.1145/3298689.3346968
Publication status	Published - 2019 Sept 10
Event	13th ACM Conference on Recommender Systems, RecSys 2019 - Copenhagen, Denmark Duration: 2019 Sept 16 → 2019 Sept 20

Publication series

Name	RecSys 2019 - 13th ACM Conference on Recommender Systems

Conference

Conference	13th ACM Conference on Recommender Systems, RecSys 2019
Country/Territory	Denmark
City	Copenhagen
Period	19-09-16 → 19-09-20

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Software
Information Systems
Computer Science Applications

Access to Document

10.1145/3298689.3346968

Cite this

Tsai, Y. C., Chen, C. Y., Ma, S. L., Wang, P. C., Chen, Y. J., Chang, Y. C., & Li, C. T. (2019). FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items. In RecSys 2019 - 13th ACM Conference on Recommender Systems (pp. 536-537). (RecSys 2019 - 13th ACM Conference on Recommender Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3298689.3346968

@inproceedings{0410fed042454ebb9e1b597bcdb82c1a,

title = "FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items",

abstract = "Financial technology (FinTech) draws much attention in these years, with the advances of machine learning and deep learning. In this work, given historical time series of stock prices of companies, we aim at forecasting upcoming anomalous fnancial items, i.e., abrupt soaring or diving stocks, in fnancial time series, and recommending the corresponding stocks to support fnancial operations. We propose a novel joint convolutional and recurrent neural network model, Financial Event Neural Network (FineNet), to forecast and recommend anomalous stocks. Experiments conducted on the time series of stock prices of 300 well-known companies exhibit the promising performance of FineNet in terms of precision and recall. We build FineNet as a Web platform for live demonstration.",

author = "Tsai, {Yu Che} and Chen, {Chih Yao} and Ma, {Shao Lun} and Wang, {Pei Chi} and Chen, {You Jia} and Chang, {Yu Chieh} and Li, {Cheng Te}",

year = "2019",

month = sep,

day = "10",

doi = "10.1145/3298689.3346968",

language = "English",

series = "RecSys 2019 - 13th ACM Conference on Recommender Systems",

publisher = "Association for Computing Machinery, Inc",

pages = "536--537",

booktitle = "RecSys 2019 - 13th ACM Conference on Recommender Systems",

note = "13th ACM Conference on Recommender Systems, RecSys 2019 ; Conference date: 16-09-2019 Through 20-09-2019",

}

Tsai, YC, Chen, CY, Ma, SL, Wang, PC, Chen, YJ, Chang, YC & Li, CT 2019, FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items. in RecSys 2019 - 13th ACM Conference on Recommender Systems. RecSys 2019 - 13th ACM Conference on Recommender Systems, Association for Computing Machinery, Inc, pp. 536-537, 13th ACM Conference on Recommender Systems, RecSys 2019, Copenhagen, Denmark, 19-09-16. https://doi.org/10.1145/3298689.3346968

FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items. / Tsai, Yu Che; Chen, Chih Yao; Ma, Shao Lun et al.
RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2019. p. 536-537 (RecSys 2019 - 13th ACM Conference on Recommender Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - FineNet

T2 - 13th ACM Conference on Recommender Systems, RecSys 2019

AU - Tsai, Yu Che

AU - Chen, Chih Yao

AU - Ma, Shao Lun

AU - Wang, Pei Chi

AU - Chen, You Jia

AU - Chang, Yu Chieh

AU - Li, Cheng Te

PY - 2019/9/10

Y1 - 2019/9/10

N2 - Financial technology (FinTech) draws much attention in these years, with the advances of machine learning and deep learning. In this work, given historical time series of stock prices of companies, we aim at forecasting upcoming anomalous fnancial items, i.e., abrupt soaring or diving stocks, in fnancial time series, and recommending the corresponding stocks to support fnancial operations. We propose a novel joint convolutional and recurrent neural network model, Financial Event Neural Network (FineNet), to forecast and recommend anomalous stocks. Experiments conducted on the time series of stock prices of 300 well-known companies exhibit the promising performance of FineNet in terms of precision and recall. We build FineNet as a Web platform for live demonstration.

AB - Financial technology (FinTech) draws much attention in these years, with the advances of machine learning and deep learning. In this work, given historical time series of stock prices of companies, we aim at forecasting upcoming anomalous fnancial items, i.e., abrupt soaring or diving stocks, in fnancial time series, and recommending the corresponding stocks to support fnancial operations. We propose a novel joint convolutional and recurrent neural network model, Financial Event Neural Network (FineNet), to forecast and recommend anomalous stocks. Experiments conducted on the time series of stock prices of 300 well-known companies exhibit the promising performance of FineNet in terms of precision and recall. We build FineNet as a Web platform for live demonstration.

UR - http://www.scopus.com/inward/record.url?scp=85073330667&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073330667&partnerID=8YFLogxK

U2 - 10.1145/3298689.3346968

DO - 10.1145/3298689.3346968

M3 - Conference contribution

T3 - RecSys 2019 - 13th ACM Conference on Recommender Systems

SP - 536

EP - 537

BT - RecSys 2019 - 13th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

Y2 - 16 September 2019 through 20 September 2019

ER -

Tsai YC, Chen CY, Ma SL, Wang PC, Chen YJ, Chang YC et al. FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items. In RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2019. p. 536-537. (RecSys 2019 - 13th ACM Conference on Recommender Systems). doi: 10.1145/3298689.3346968

FineNet: A joint convolutional and recurrent neural network model to forecast and recommend anomalous financial items

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this