DEVELOPMENT... OpenML
Data
FOREX_audchf-hour-High

FOREX_audchf-hour-High

active ARFF Publicly available Visibility: public Uploaded 03-06-2019 by Jason
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • finance forex forex_high forex_hour study_219
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Source: Dukascopy Historical Data Feed https://www.dukascopy.com/swiss/english/marketwatch/historical/ Edited by: Fabian Schut # Data Description This is the historical price data of the FOREX AUD/CHF from Dukascopy. One instance (row) is one candlestick of one hour. The whole dataset has the data range from 1-1-2018 to 13-12-2018 and does not include the weekends, since the FOREX is not traded in the weekend. The timezone of the feature Timestamp is Europe/Amsterdam. The class attribute is the direction of the mean of the High_Bid and the High_Ask of the following hour, relative to the High_Bid and High_Ask mean of the current minute. This means the class attribute is True when the mean High price is going up the following hour, and the class attribute is False when the mean High price is going down (or stays the same) the following hour. Note that this is a hypothetical task, meant for scientific purposes only. Realistic trade strategies can only be applied to predictions on 'Close'-attributes (also available). # Attributes `Timestamp`: The time of the current data point (Europe/Amsterdam) `Bid_Open`: The bid price at the start of this time interval `Bid_High`: The highest bid price during this time interval `Bid_Low`: The lowest bid price during this time interval `Bid_Close`: The bid price at the end of this time interval `Bid_Volume`: The number of times the Bid Price changed within this time interval `Ask_Open`: The ask price at the start of this time interval `Ask_High`: The highest ask price during this time interval `Ask_Low`: The lowest ask price during this time interval `Ask_Close`: The ask price at the end of this time interval `Ask_Volume`: The number of times the Ask Price changed within this time interval `Class`: Whether the average price will go up during the next interval

12 features

Class (target)nominal2 unique values
0 missing
Timestampdate43825 unique values
0 missing
Bid_Opennumeric18838 unique values
0 missing
Bid_Highnumeric18587 unique values
0 missing
Bid_Lownumeric18896 unique values
0 missing
Bid_Closenumeric18762 unique values
0 missing
Bid_Volumenumeric42571 unique values
0 missing
Ask_Opennumeric19170 unique values
0 missing
Ask_Highnumeric19160 unique values
0 missing
Ask_Lownumeric19012 unique values
0 missing
Ask_Closenumeric19072 unique values
0 missing
Ask_Volumenumeric42629 unique values
0 missing
Show all 12 features

19 properties

NumberOfInstances
43825
Number of instances (rows) of the dataset.
NumberOfFeatures
12
Number of attributes (columns) of the dataset.
NumberOfClasses
2
Number of distinct values of the target attribute (if it is nominal).
NumberOfMissingValues
0
Number of missing values in the dataset.
NumberOfInstancesWithMissingValues
0
Number of instances with at least one value missing.
NumberOfNumericFeatures
11
Number of numeric attributes.
NumberOfSymbolicFeatures
1
Number of nominal attributes.
PercentageOfSymbolicFeatures
8.33
Percentage of nominal attributes.
AutoCorrelation
0.54
Average class difference between consecutive instances.
PercentageOfNumericFeatures
91.67
Percentage of numeric attributes.
PercentageOfMissingValues
0
Percentage of missing values.
PercentageOfInstancesWithMissingValues
0
Percentage of instances having missing values.
PercentageOfBinaryFeatures
8.33
Percentage of binary attributes.
NumberOfBinaryFeatures
1
Number of binary attributes.
MinorityClassSize
21344
Number of instances belonging to the least frequent class.
MinorityClassPercentage
48.7
Percentage of instances belonging to the least frequent class.
MajorityClassSize
22481
Number of instances belonging to the most frequent class.
MajorityClassPercentage
51.3
Percentage of instances belonging to the most frequent class.
Dimensionality
0
Number of attributes divided by the number of instances.
Show all 19 properties

10 tasks

Supervised Classification on FOREX_audchf-hour-High
0 runs - estimation_procedure: 20% Holdout (Ordered) - target_feature: Class
Supervised Classification on FOREX_audchf-hour-High
0 runs - estimation_procedure: 10-fold Crossvalidation - target_feature: Class
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Clustering on FOREX_audchf-hour-High
0 runs - estimation_procedure: 50 times Clustering
Define a new task