{"id":8050,"date":"2026-04-09T22:17:35","date_gmt":"2026-04-10T03:17:35","guid":{"rendered":"https:\/\/proinvesting.co\/?p=8050"},"modified":"2026-04-09T23:05:15","modified_gmt":"2026-04-10T04:05:15","slug":"neural-network-classifier-trained-on-gld","status":"publish","type":"post","link":"https:\/\/proinvesting.co\/es\/neural-network-classifier-trained-on-gld\/","title":{"rendered":"Neural network classifier trained on GLD"},"content":{"rendered":"

[et_pb_section fb_built=”1″ admin_label=”Header” _builder_version=”4.18.0″ background_color=”RGBA(255,255,255,0)” background_enable_image=”off” custom_padding=”0px|0px|0|0px|false|false” locked=”off” global_colors_info=”{}”][et_pb_row column_structure=”3_4,1_4″ use_custom_gutter=”on” gutter_width=”2″ _builder_version=”4.16″ max_width=”1280px” custom_margin=”|auto||2px||” custom_padding=”13px||0px|||” use_custom_width=”on” custom_width_px=”1280px” global_colors_info=”{}”][et_pb_column type=”3_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text _builder_version=”4.18.0″ _dynamic_attributes=”content” text_font=”Poppins|700|||||||” text_text_color=”#474747″ text_font_size=”35px” text_line_height=”1.3em” ul_font=”||||||||” ol_font=”||||||||” header_font=”Work Sans|700|||||||” header_font_size=”55px” header_line_height=”1.5em” header_3_font=”||||||||” header_4_font=”||||||||” header_5_font=”||||||||” header_6_font=”||||||||” custom_padding=”||10px||false|false” text_font_size_tablet=”40px” text_font_size_phone=”30px” text_font_size_last_edited=”on|desktop” header_font_size_tablet=”40px” header_font_size_phone=”30px” header_font_size_last_edited=”on|desktop” border_color_all=”#FFFFFF” border_width_bottom=”4px” locked=”off” global_colors_info=”{}” header_2_font_size__hover=”26px” header_2_font_size__hover_enabled=”26px” header_2_letter_spacing__hover=”0px” header_2_letter_spacing__hover_enabled=”0px” header_2_line_height__hover=”1em” header_2_line_height__hover_enabled=”1em” header_2_text_shadow_style__hover=”none” header_2_text_shadow_style__hover_enabled=”none” header_2_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_2_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)”]@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF90aXRsZSIsInNldHRpbmdzIjp7ImJlZm9yZSI6IiIsImFmdGVyIjoiIn19@[\/et_pb_text][et_pb_text _builder_version=”4.18.0″ _dynamic_attributes=”content” text_font=”Work Sans|600|||||||” text_text_color=”#FFFFFF” text_line_height=”1.4em” link_font=”||||||||” link_text_color=”#1a0a38″ header_text_color=”#FFFFFF” locked=”off” global_colors_info=”{}”]@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9jb21tZW50X2NvdW50Iiwic2V0dGluZ3MiOnsiYmVmb3JlIjoiIiwiYWZ0ZXIiOiIgQ29tbWVudHMgIiwibGlua190b19jb21tZW50c19wYWdlIjoib24ifX0=@[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_blurb title=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9hdXRob3IiLCJzZXR0aW5ncyI6eyJiZWZvcmUiOiJXcml0dGVuIGJ5ICIsImFmdGVyIjoiIiwibmFtZV9mb3JtYXQiOiJkaXNwbGF5X25hbWUiLCJsaW5rIjoib24iLCJsaW5rX2Rlc3RpbmF0aW9uIjoiYXV0aG9yX2FyY2hpdmUifX0=@” image=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9hdXRob3JfcHJvZmlsZV9waWN0dXJlIiwic2V0dGluZ3MiOnt9fQ==@” icon_placement=”left” image_icon_width=”32px” content_max_width=”1100px” _builder_version=”4.18.0″ _dynamic_attributes=”image,title” header_font=”Work Sans|600|||||||” header_text_align=”left” header_text_color=”#000000″ header_font_size=”18px” header_line_height=”1.5em” body_font=”Work Sans||||||||” text_orientation=”center” background_layout=”dark” custom_margin=”|||-8px” animation=”off” border_radii_image=”on|100px|100px|100px|100px” image_max_width=”32px” locked=”off” global_colors_info=”{}” icon_color__hover=”#00ac69″ box_shadow_color__hover_enabled=”rgba(0,0,0,0.3)” box_shadow_color__hover=”rgba(0,0,0,0.3)” box_shadow_style__hover=”none” box_shadow_style__hover_enabled=”none” use_background_color_gradient__hover=”off” use_background_color_gradient__hover_enabled=”off” background_color_gradient_start__hover=”#2b87da” background_color_gradient_start__hover_enabled=”#2b87da” background_color_gradient_end__hover=”#29c4a9″ background_color_gradient_end__hover_enabled=”#29c4a9″ background_color_gradient_type__hover=”linear” background_color_gradient_type__hover_enabled=”linear” background_color_gradient_direction__hover=”180deg” background_color_gradient_direction__hover_enabled=”180deg” background_color_gradient_direction_radial__hover=”center” background_color_gradient_direction_radial__hover_enabled=”center” background_color_gradient_start_position__hover=”0%” background_color_gradient_start_position__hover_enabled=”0%” background_color_gradient_end_position__hover=”100%” background_color_gradient_end_position__hover_enabled=”100%” background_color_gradient_overlays_image__hover=”off” background_color_gradient_overlays_image__hover_enabled=”off” parallax__hover=”off” parallax__hover_enabled=”off” parallax_method__hover=”on” parallax_method__hover_enabled=”on” background_size__hover=”cover” background_size__hover_enabled=”cover” background_position__hover=”center” background_position__hover_enabled=”center” background_repeat__hover=”no-repeat” background_repeat__hover_enabled=”no-repeat” background_blend__hover=”normal” background_blend__hover_enabled=”normal” allow_player_pause__hover=”off” allow_player_pause__hover_enabled=”off” background_video_pause_outside_viewport__hover=”on” background_video_pause_outside_viewport__hover_enabled=”on” background_color_gradient_stops__hover=”#2b87da 0%|#29c4a9 100%”][\/et_pb_blurb][et_pb_blurb title=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9kYXRlIiwic2V0dGluZ3MiOnsiYmVmb3JlIjoiIiwiYWZ0ZXIiOiIiLCJkYXRlX2Zvcm1hdCI6ImRlZmF1bHQiLCJjdXN0b21fZGF0ZV9mb3JtYXQiOiIifX0=@” use_icon=”on” font_icon=”||divi||400″ icon_color=”#00ac69″ icon_placement=”left” image_icon_width=”16px” content_max_width=”1100px” _builder_version=”4.18.0″ _dynamic_attributes=”title” header_font=”Work Sans|600|||||||” header_text_align=”left” header_text_color=”#000000″ header_font_size=”14px” text_orientation=”center” background_layout=”dark” custom_margin=”|||” animation=”off” icon_font_size=”16px” locked=”off” global_colors_info=”{}” icon_color__hover=”#00ac69″ box_shadow_color__hover_enabled=”rgba(0,0,0,0.3)” box_shadow_color__hover=”rgba(0,0,0,0.3)” box_shadow_style__hover=”none” box_shadow_style__hover_enabled=”none” use_background_color_gradient__hover=”off” use_background_color_gradient__hover_enabled=”off” background_color_gradient_start__hover=”#2b87da” background_color_gradient_start__hover_enabled=”#2b87da” background_color_gradient_end__hover=”#29c4a9″ background_color_gradient_end__hover_enabled=”#29c4a9″ background_color_gradient_type__hover=”linear” background_color_gradient_type__hover_enabled=”linear” background_color_gradient_direction__hover=”180deg” background_color_gradient_direction__hover_enabled=”180deg” background_color_gradient_direction_radial__hover=”center” background_color_gradient_direction_radial__hover_enabled=”center” background_color_gradient_start_position__hover=”0%” background_color_gradient_start_position__hover_enabled=”0%” background_color_gradient_end_position__hover=”100%” background_color_gradient_end_position__hover_enabled=”100%” background_color_gradient_overlays_image__hover=”off” background_color_gradient_overlays_image__hover_enabled=”off” parallax__hover=”off” parallax__hover_enabled=”off” parallax_method__hover=”on” parallax_method__hover_enabled=”on” background_size__hover=”cover” background_size__hover_enabled=”cover” background_position__hover=”center” background_position__hover_enabled=”center” background_repeat__hover=”no-repeat” background_repeat__hover_enabled=”no-repeat” background_blend__hover=”normal” background_blend__hover_enabled=”normal” allow_player_pause__hover=”off” allow_player_pause__hover_enabled=”off” background_video_pause_outside_viewport__hover=”on” background_video_pause_outside_viewport__hover_enabled=”on” body_letter_spacing__hover=”0px” body_letter_spacing__hover_enabled=”0px” body_text_shadow_style__hover=”none” body_text_shadow_style__hover_enabled=”none” body_text_shadow_color__hover=”rgba(0,0,0,0.4)” body_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” background_color_gradient_stops__hover=”#2b87da 0%|#29c4a9 100%”][\/et_pb_blurb][et_pb_blurb title=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9jYXRlZ29yaWVzIiwic2V0dGluZ3MiOnsiYmVmb3JlIjoiIiwiYWZ0ZXIiOiIiLCJsaW5rX3RvX3Rlcm1fcGFnZSI6Im9uIiwic2VwYXJhdG9yIjoiIHwgIiwiY2F0ZWdvcnlfdHlwZSI6InBhZ2VfY2F0ZWdvcnkifX0=@” use_icon=”on” font_icon=”||divi||400″ icon_color=”#00ac69″ icon_placement=”left” image_icon_width=”16px” content_max_width=”1100px” _builder_version=”4.18.0″ _dynamic_attributes=”title” header_font=”Work Sans|600|||||||” header_text_align=”left” header_text_color=”#000000″ header_font_size=”14px” text_orientation=”center” custom_margin=”|||” animation=”off” icon_font_size=”16px” locked=”off” global_colors_info=”{}” icon_color__hover=”#00ac69″ box_shadow_color__hover_enabled=”rgba(0,0,0,0.3)” box_shadow_color__hover=”rgba(0,0,0,0.3)” box_shadow_style__hover=”none” box_shadow_style__hover_enabled=”none” use_background_color_gradient__hover=”off” use_background_color_gradient__hover_enabled=”off” background_color_gradient_start__hover=”#2b87da” background_color_gradient_start__hover_enabled=”#2b87da” background_color_gradient_end__hover=”#29c4a9″ background_color_gradient_end__hover_enabled=”#29c4a9″ background_color_gradient_type__hover=”linear” background_color_gradient_type__hover_enabled=”linear” background_color_gradient_direction__hover=”180deg” background_color_gradient_direction__hover_enabled=”180deg” background_color_gradient_direction_radial__hover=”center” background_color_gradient_direction_radial__hover_enabled=”center” background_color_gradient_start_position__hover=”0%” background_color_gradient_start_position__hover_enabled=”0%” background_color_gradient_end_position__hover=”100%” background_color_gradient_end_position__hover_enabled=”100%” background_color_gradient_overlays_image__hover=”off” background_color_gradient_overlays_image__hover_enabled=”off” parallax__hover=”off” parallax__hover_enabled=”off” parallax_method__hover=”on” parallax_method__hover_enabled=”on” background_size__hover=”cover” background_size__hover_enabled=”cover” background_position__hover=”center” background_position__hover_enabled=”center” background_repeat__hover=”no-repeat” background_repeat__hover_enabled=”no-repeat” background_blend__hover=”normal” background_blend__hover_enabled=”normal” allow_player_pause__hover=”off” allow_player_pause__hover_enabled=”off” background_video_pause_outside_viewport__hover=”on” background_video_pause_outside_viewport__hover_enabled=”on” body_letter_spacing__hover=”0px” body_letter_spacing__hover_enabled=”0px” body_text_shadow_style__hover=”none” body_text_shadow_style__hover_enabled=”none” body_text_shadow_color__hover=”rgba(0,0,0,0.4)” body_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” background_color_gradient_stops__hover=”#2b87da 0%|#29c4a9 100%”][\/et_pb_blurb][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ use_custom_gutter=”on” gutter_width=”2″ specialty=”on” padding_1_tablet=”0px||” padding_1_last_edited=”off|desktop” admin_label=”Content” _builder_version=”4.16″ background_size=”contain” background_position=”top_center” inner_max_width=”1280px” custom_margin=”4px|||||” custom_padding=”0|0px|54px|0px|false|false” use_custom_width=”on” custom_width_px=”1280px” global_colors_info=”{}” background_size__hover=”cover” background_size__hover_enabled=”cover” background_position__hover=”center” background_position__hover_enabled=”center” use_background_color_gradient__hover=”off” use_background_color_gradient__hover_enabled=”off” background_color_gradient_start__hover=”#2b87da” background_color_gradient_start__hover_enabled=”#2b87da” background_color_gradient_end__hover=”#29c4a9″ background_color_gradient_end__hover_enabled=”#29c4a9″ background_color_gradient_type__hover=”linear” background_color_gradient_type__hover_enabled=”linear” background_color_gradient_direction__hover=”180deg” background_color_gradient_direction__hover_enabled=”180deg” background_color_gradient_direction_radial__hover=”center” background_color_gradient_direction_radial__hover_enabled=”center” background_color_gradient_start_position__hover=”0%” background_color_gradient_start_position__hover_enabled=”0%” background_color_gradient_end_position__hover=”100%” background_color_gradient_end_position__hover_enabled=”100%” background_color_gradient_overlays_image__hover=”off” background_color_gradient_overlays_image__hover_enabled=”off” parallax__hover=”off” parallax__hover_enabled=”off” parallax_method__hover=”on” parallax_method__hover_enabled=”on” background_repeat__hover=”no-repeat” background_repeat__hover_enabled=”no-repeat” background_blend__hover=”normal” background_blend__hover_enabled=”normal” allow_player_pause__hover=”off” allow_player_pause__hover_enabled=”off” background_video_pause_outside_viewport__hover=”on” background_video_pause_outside_viewport__hover_enabled=”on” background_color_gradient_stops__hover=”#2b87da 0%|#29c4a9 100%”][et_pb_column type=”3_4″ specialty_columns=”3″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” padding_tablet__hover=”0px||” padding_last_edited__hover=”off|desktop” parallax__hover=”off” parallax_method__hover=”on” padding_tablet=”0px||” padding_last_edited=”off|desktop” custom_padding__hover=”|||”][et_pb_row_inner _builder_version=”4.16″ custom_margin=”23px|||||” custom_padding=”0px|||||” locked=”off” global_colors_info=”{}” parallax_1__hover=”off” parallax_1__hover_enabled=”off” parallax_2__hover=”off” parallax_2__hover_enabled=”off” parallax_3__hover=”off” parallax_3__hover_enabled=”off” parallax_4__hover=”off” parallax_4__hover_enabled=”off” parallax_method_1__hover=”on” parallax_method_1__hover_enabled=”on” parallax_method_2__hover=”on” parallax_method_2__hover_enabled=”on” parallax_method_3__hover=”on” parallax_method_3__hover_enabled=”on” parallax_method_4__hover=”on” parallax_method_4__hover_enabled=”on” use_background_color_gradient__hover=”off” use_background_color_gradient__hover_enabled=”off” background_color_gradient_start__hover=”#2b87da” background_color_gradient_start__hover_enabled=”#2b87da” background_color_gradient_end__hover=”#29c4a9″ background_color_gradient_end__hover_enabled=”#29c4a9″ background_color_gradient_type__hover=”linear” background_color_gradient_type__hover_enabled=”linear” background_color_gradient_direction__hover=”180deg” background_color_gradient_direction__hover_enabled=”180deg” background_color_gradient_direction_radial__hover=”center” background_color_gradient_direction_radial__hover_enabled=”center” background_color_gradient_start_position__hover=”0%” background_color_gradient_start_position__hover_enabled=”0%” background_color_gradient_end_position__hover=”100%” background_color_gradient_end_position__hover_enabled=”100%” background_color_gradient_overlays_image__hover=”off” background_color_gradient_overlays_image__hover_enabled=”off” parallax__hover=”off” parallax__hover_enabled=”off” parallax_method__hover=”on” parallax_method__hover_enabled=”on” background_size__hover=”cover” background_size__hover_enabled=”cover” background_position__hover=”center” background_position__hover_enabled=”center” background_repeat__hover=”no-repeat” background_repeat__hover_enabled=”no-repeat” background_blend__hover=”normal” background_blend__hover_enabled=”normal” allow_player_pause__hover=”off” allow_player_pause__hover_enabled=”off” background_video_pause_outside_viewport__hover=”on” background_video_pause_outside_viewport__hover_enabled=”on” use_custom_gutter__hover=”off” use_custom_gutter__hover_enabled=”off” gutter_width__hover=”3″ gutter_width__hover_enabled=”3″ make_equal__hover=”off” make_equal__hover_enabled=”off” border_radii__hover=”on||||” border_radii__hover_enabled=”on||||” box_shadow_style__hover=”none” box_shadow_style__hover_enabled=”none” box_shadow_color__hover=”rgba(0,0,0,0.3)” box_shadow_color__hover_enabled=”rgba(0,0,0,0.3)” max_width__hover=”100%” max_width__hover_enabled=”100%” filter_hue_rotate__hover=”0deg” filter_hue_rotate__hover_enabled=”0deg” filter_saturate__hover=”100%” filter_saturate__hover_enabled=”100%” filter_brightness__hover=”100%” filter_brightness__hover_enabled=”100%” filter_contrast__hover=”100%” filter_contrast__hover_enabled=”100%” filter_invert__hover=”0%” filter_invert__hover_enabled=”0%” filter_sepia__hover=”0%” filter_sepia__hover_enabled=”0%” filter_opacity__hover=”100%” filter_opacity__hover_enabled=”100%” filter_blur__hover=”0px” filter_blur__hover_enabled=”0px” mix_blend_mode__hover=”normal” mix_blend_mode__hover_enabled=”normal” animation_style__hover=”none” animation_style__hover_enabled=”none” animation_repeat__hover=”once” animation_repeat__hover_enabled=”once” animation_direction__hover=”center” animation_direction__hover_enabled=”center” animation_duration__hover=”1000ms” animation_duration__hover_enabled=”1000ms” animation_delay__hover=”0ms” animation_delay__hover_enabled=”0ms” animation_intensity_slide__hover=”50%” animation_intensity_slide__hover_enabled=”50%” animation_intensity_zoom__hover=”50%” animation_intensity_zoom__hover_enabled=”50%” animation_intensity_flip__hover=”50%” animation_intensity_flip__hover_enabled=”50%” animation_intensity_fold__hover=”50%” animation_intensity_fold__hover_enabled=”50%” animation_intensity_roll__hover=”50%” animation_intensity_roll__hover_enabled=”50%” animation_starting_opacity__hover=”0%” animation_starting_opacity__hover_enabled=”0%” animation_speed_curve__hover=”ease-in-out” animation_speed_curve__hover_enabled=”ease-in-out” hover_transition_duration__hover=”300ms” hover_transition_duration__hover_enabled=”300ms” hover_transition_delay__hover=”0ms” hover_transition_delay__hover_enabled=”0ms” hover_transition_speed_curve__hover=”ease” hover_transition_speed_curve__hover_enabled=”ease” background_color_gradient_stops__hover=”#2b87da 0%|#29c4a9 100%”][et_pb_column_inner saved_specialty_column_type=”3_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” parallax__hover=”off” parallax__hover_enabled=”off” parallax_method__hover=”on” parallax_method__hover_enabled=”on” custom_padding__hover=”|||”][et_pb_image src=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9mZWF0dXJlZF9pbWFnZSIsInNldHRpbmdzIjp7fX0=@” force_fullwidth=”on” align_tablet=”center” align_phone=”center” align_last_edited=”on|desktop” _builder_version=”4.16″ _dynamic_attributes=”src” border_radii=”on|5px|5px|5px|5px” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ text_font=”||||||||” text_line_height=”2em” header_font=”||||||||” header_2_font=”Work Sans|700|||||||” header_2_font_size=”25px” header_2_line_height=”1.5em” max_width_tablet=”” max_width_phone=”” max_width_last_edited=”on|tablet” header_2_font_size_tablet=”30px” header_2_font_size_phone=”15px” header_2_font_size_last_edited=”on|desktop” locked=”off” inline_fonts=”Poppins” global_colors_info=”{}” header_font_size__hover=”30px” header_font_size__hover_enabled=”30px” header_letter_spacing__hover=”0px” header_letter_spacing__hover_enabled=”0px” header_text_shadow_style__hover=”none” header_text_shadow_style__hover_enabled=”none” header_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” header_2_font_size__hover=”26px” header_2_font_size__hover_enabled=”26px” header_2_letter_spacing__hover=”0px” header_2_letter_spacing__hover_enabled=”0px” header_2_line_height__hover=”1em” header_2_line_height__hover_enabled=”1em” header_2_text_shadow_style__hover=”none” header_2_text_shadow_style__hover_enabled=”none” header_2_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_2_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” header_3_font_size__hover=”22px” header_3_font_size__hover_enabled=”22px” header_3_letter_spacing__hover=”0px” header_3_letter_spacing__hover_enabled=”0px” header_3_line_height__hover=”1em” header_3_line_height__hover_enabled=”1em” header_3_text_shadow_style__hover=”none” header_3_text_shadow_style__hover_enabled=”none” header_3_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_3_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” header_4_font_size__hover=”18px” header_4_font_size__hover_enabled=”18px” header_4_letter_spacing__hover=”0px” header_4_letter_spacing__hover_enabled=”0px” header_4_line_height__hover=”1em” header_4_line_height__hover_enabled=”1em” header_4_text_shadow_style__hover=”none” header_4_text_shadow_style__hover_enabled=”none” header_4_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_4_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” header_5_font_size__hover=”16px” header_5_font_size__hover_enabled=”16px” header_5_letter_spacing__hover=”0px” header_5_letter_spacing__hover_enabled=”0px” header_5_line_height__hover=”1em” header_5_line_height__hover_enabled=”1em” header_5_text_shadow_style__hover=”none” header_5_text_shadow_style__hover_enabled=”none” header_5_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_5_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” header_6_font_size__hover=”14px” header_6_font_size__hover_enabled=”14px” header_6_letter_spacing__hover=”0px” header_6_letter_spacing__hover_enabled=”0px” header_6_line_height__hover=”1em” header_6_line_height__hover_enabled=”1em” header_6_text_shadow_style__hover=”none” header_6_text_shadow_style__hover_enabled=”none” header_6_text_shadow_color__hover=”rgba(0,0,0,0.4)” header_6_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)” text_letter_spacing__hover=”0px” text_letter_spacing__hover_enabled=”0px” text_text_shadow_style__hover=”none” text_text_shadow_style__hover_enabled=”none” text_text_shadow_color__hover=”rgba(0,0,0,0.4)” text_text_shadow_color__hover_enabled=”rgba(0,0,0,0.4)”]<\/p>\n

When the Classifier
Doesn’t Know \u2014
That’s the Signal.<\/em><\/h1>\n

A neural network classifier trained on $GLD not only detects crowded trades \u2014 its zone of maximum uncertainty anticipates regime inflections that rolling volatility confirms too late.<\/span><\/p>\n

 <\/p>\n

What Most Positioning Models Fail to Capture<\/h2>\n

Standard positioning frameworks \u2014 historical percentiles, flow z-scores, net COT \u2014 all answer the same question: where is positioning right now?<\/em> They are descriptive. They capture the level but not the market structure that produces it.<\/p>\n

There is a different, more valuable question: how well does the current environment fit the expectations the model built from history?<\/strong> When returns start behaving in ways the classifier hasn’t seen before, that divergence is information \u2014 and it arrives before the trade reverses.<\/p>\n

This is exactly what a neural network classifier trained on implicit positioning captures. Its zone of maximum uncertainty \u2014 where it assigns nearly equal probabilities to all three regimes \u2014 is not a model failure. It is the cleanest signal the model produces.<\/p>\n

“Markets don’t reverse on news. They reverse on positioning. And positioning leaves a trail in price \u2014 if you know how to read it.”<\/em><\/p>\n

FRAMEWORK PRINCIPLE \u00b7 ALPHA CENTAURI PROGRAM<\/div>\n
<\/span><\/div>\n
<\/div>\n

[\/et_pb_text][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” locked=”off” global_colors_info=”{}”]<\/p>\n

The Positioning Proxy: Built From Price<\/h2>\n

Without access to real-time COT data, we infer positioning from price structure. The logic is precise: if $GLD has risen consistently over 63 trading days (~3 months), there is a mass of accumulated buyers sitting on unrealized gains. That is a structurally crowded trade. The reversal is not caused by the catalyst \u2014 it is caused by the structure.<\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/Screenshot-2026-04-09-at-7.59.59-PM.png&#8221<\/a>; title_text=”PYTHON \u00b7 FEATURE ENGINEERING (YFINANCE)” _builder_version=”4.18.0″ _module_preset=”default” border_radii=”on|20px|20px|20px|20px” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n\n\n\n\n\n\n\n
REGIME<\/th>\nCONDITION<\/th>\nOPERATIONAL SIGNAL<\/th>\nINTERPRETATION<\/th>\n<\/tr>\n<\/thead>\n
Crowded Long<\/td>\nPercentile > 80<\/td>\nShort bias<\/span><\/td>\nAccumulated buyers, few marginal buyers remaining. Asymmetric downside risk.<\/td>\n<\/tr>\n
Neutral<\/td>\nPercentile 20\u201380<\/td>\nNo bias<\/span><\/td>\nPositioning within historical range. Classifier operates with high regime certainty.<\/td>\n<\/tr>\n
Crowded Short<\/td>\nPercentile < 20<\/td>\nLong bias<\/span><\/td>\nMass of trapped shorts. Any positive catalyst can trigger a squeeze.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 <\/p>\n

The Architecture: MLPClassifier Over the Positioning Space<\/h2>\n

The classifier follows the same architecture Matthew Dixon demonstrates in his 2019 notebook on deep classifiers in finance \u2014 but instead of separating synthetic half-moons, it separates real market regimes<\/strong> in the z-score \u00d7 realized volatility space.<\/p>\n

The advantage over a binary logit is structural: the decision boundary in this feature space is non-linear<\/strong>. Market regimes are not separable with a straight line. The MLP with ReLU activations learns that curvature directly from data \u2014 no analyst encodes it.<\/p>\n

ARCHITECTURE \u00b7 MLPCLASSIFIER (SKLEARN)<\/div>\n
Input [z_score, vol_21] \u2192 (16, ReLU) \u2192 (8, ReLU) \u2192 Softmax \u2192 3 clases<\/div>\n
f(z, v) = argmax P(regime | z, v ; W, b)<\/div>\n
Training accuracy: 96.0%<\/span> \u00a0\u00b7\u00a0 Normalization: StandardScaler over expanding window<\/span> \u00a0\u00b7\u00a0Data: GLD 2015\u20132026 \u00b7 yfinance<\/span><\/div>\n

 <\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/F1.png.jpeg&#8221<\/a>; title_text=”F1.png” _builder_version=”4.18.0″ _module_preset=”default” border_radii=”on|20px|20px|20px|20px” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

<\/div>\n
\n
FIGURE 1<\/strong><\/div>\n

MLPClassifier decision boundary (2 hidden layers, ReLU) in z-score \u00d7 realized volatility space. Green = Crowded Short (long bias). Gray = Neutral. Red = Crowded Long (short bias). Dashed lines mark the learned non-linear boundaries \u2014 inaccessible to a standard logistic classifier. Data: GLD 2015\u20132026 via Yahoo Finance.<\/p>\n

The curved boundary between Neutral and Crowded Long reveals a pattern not explicitly encoded: at high realized volatility levels, a moderate z-score is sufficient to classify as crowded. The latent selling pressure in a volatile environment is structurally larger. The model learns this from data, not from rules.<\/span><\/p>\n<\/div>\n

 <\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

The Transformation: Input Space \u2192 Hidden Layer<\/h2>\n

Dixon’s 2019 notebook demonstrates that a MLP’s hidden layers don’t just classify \u2014 they transform the feature space<\/strong> to make linearly separable what wasn’t in the original input. The same happens here with real $GLD data.<\/p>\n

With a final hidden layer of 2 units (directly plottable), we can visualize exactly what the network did: it takes a space where the three regimes overlap, and builds a representation where the clusters are linearly separable.<\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/F2.jpeg&#8221<\/a>; title_text=”F2″ _builder_version=”4.18.0″ _module_preset=”default” border_radii=”on|20px|20px|20px|20px” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Figure 2. <\/strong><\/em>Transformation from input space (left) to the 2-unit hidden layer space (right). In the input, the three regimes overlap \u2014 no linear classifier separates them. After the ReLU transformation, clusters reorganize into linearly separable zones. Replicates Dixon’s (2019) make_moons analysis, applied to a decade of real $GLD data.<\/p>\n

.<\/em><\/p>\n

[\/et_pb_text][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

The Signal Few Exploit: The Maximum Uncertainty Zone<\/h2>\n

Most classifier users only read the final output: “regime = Crowded Long”<\/em>. They ignore the internal class probabilities. That is a mistake with real operational cost.<\/p>\n

When the classifier assigns probabilities close to 33%\u201333%\u201333%<\/strong> across the three regimes, it is not confused \u2014 it is detecting that the market is at a structural transition point. That state of maximum model uncertainty consistently precedes regime changes.<\/p>\n

 <\/p>\n

THE KEY DISTINCTION<\/strong><\/div>\n
<\/strong><\/div>\n
<\/strong><\/div>\n
\u00a0<\/strong><\/div>\n
<\/div>\n
<\/div>\n
<\/div>\n
\n
\n
PERCENTILE \/ Z-SCORE<\/span><\/strong><\/div>\n

Describes the positioning level. Where are we now? Retrospective. Rises after crowding has already built. A coincident indicator \u2014 not a reversal indicator.<\/p>\n<\/div>\n

\n
PROBANILITY<\/strong><\/span>\u00a0<\/div>\n

Measures the model’s structural uncertainty about the current regime. Rises when returns deviate from historical patterns in feature space. A leading indicator of transition.<\/p>\n

 <\/p>\n

The practical difference: in $GLD reversal episodes, the classifier’s maximum uncertainty zone (high probability entropy) appears <\/span>before the percentile crosses back to neutral range<\/strong>. The model detects that structure is changing before price confirms it.<\/span><\/p>\n

<\/span><\/p>\n

Vista Completa: Precio + Probabilidades de Regime ML<\/h2>\n<\/div>\n<\/div>\n
\n
<\/div>\n<\/div>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/F3.gif&#8221<\/a>; title_text=”F3″ _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Figure 3. <\/strong>Evolution of $GLD price over time \u2014 animation built with an expanding window from 2010. Each frame advances 40 trading days. The accumulation and reversal pattern is visible in price structure, not price level. Data: Yahoo Finance \u00b7 gif generated with imageio.<\/em><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/F4.gif&#8221<\/a>; title_text=”F4″ _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

\n

Figure 4.<\/strong> Evolution of the positioning z-score with \u00b12\u03c3 extreme zones \u2014 real-time animation of the crowding proxy building. Each spike above +2\u03c3 corresponds to a Crowded Long period in the classifier. Crosses below the lower band signal potential Crowded Short conditions. Data: Yahoo Finance \u00b7 yfinance \u00b7 sklearn.<\/em><\/p>\n


The three-row panel integrates the framework layers: price, Crowded Long probability, and Crowded Short probability. The joint reading reveals the regime transition process<\/strong> \u2014 not visible in any individual layer.
<\/span><\/p>\n

\n<\/div>\n

 <\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/Screenshot-2026-04-09-at-8.12.57-PM.png&#8221<\/a>; title_text=”F5″ _builder_version=”4.18.0″ _module_preset=”default” border_radii=”on|20px|20px|20px|20px” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

\n

Figure 5.<\/strong> Top panel: $GLD price with ML regime zones shaded (red = Crowded Long, green = Crowded Short). \u25b2 marks long bias (crowded short detected), \u25bc marks short bias (crowded long). Center panel: P(Crowded Long) \u2014 exceeds 0.5 before price consolidates. Bottom panel: P(Crowded Short) \u2014 spikes signal potential squeeze conditions. MLPClassifier (32\u219216\u21928, ReLU) \u00b7 5 features \u00b7 GLD 2015\u20132026.<\/em><\/p>\n

<\/em><\/p>\n

<\/em><\/p>\n<\/div>\n

Why This Complements (and Doesn’t Replace) the Percentile<\/h2>\n

 <\/p>\n

\n
TOOL 01<\/strong><\/div>\n
Percentile \/ Z-score<\/div>\n

Measures accumulated positioning pressure. High precision in stationary regimes. Informs on structural level \u2014 how loaded the trade is.<\/p>\n<\/div>\n

\n
TOOL 02<\/strong><\/div>\n
ML Classifier Probability<\/div>\n

Measures the model’s certainty about the current regime. High sensitivity at transition points. Informs on structural stability.<\/p>\n<\/div>\n

\n
HIGH-CONVICTION SIGNAL<\/div>\n
Extreme percentile + high certainty<\/div>\n

Trade is clearly crowded and the model has high structural confidence. Asymmetric risk is confirmed by both dimensions simultaneously.<\/p>\n<\/div>\n

\n
WARNING SIGNAL<\/div>\n
Extreme percentile + low certainty<\/div>\n

Trade is crowded at the level but the model detects structural incoherence. Classifier uncertainty suggests the regime may already be in active transition.<\/p>\n<\/div>\n

[\/et_pb_text][et_pb_image src=”https:\/\/proinvesting.co\/wp-content\/uploads\/2026\/04\/Screenshot-2026-04-09-at-8.15.03-PM.png&#8221<\/a>; title_text=”F6″ _builder_version=”4.18.0″ _module_preset=”default” border_radii=”on|20px|20px|20px|20px” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

\n

The combination of both dimensions \u2014 positioning level and model certainty \u2014 is the signal architecture Alpha Centauri uses to filter high-conviction trades from those where structure is ambiguous.<\/p>\n<\/section>\n

\n
\n

08<\/span><\/p>\n

<\/div>\n<\/div>\n

Model Limitations<\/h2>\n

The credibility of a systematic framework is built by being explicit about what it cannot do. This classifier has three structural limitations that should inform how it is used operationally:<\/p>\n

\n
\n
01. Proxy \u2260 real positioning<\/span><\/div>\n

Return accumulation is an approximation. It does not capture OTC flows, options, institutional hedges, or futures inventory. It infers structural pressure \u2014 not real positioning.<\/p>\n<\/div>\n

\n
02. Overfitting on self-derived labels<\/span><\/div>\n

The classifier was trained on labels derived from the same proxy. The 96% accuracy reflects internal consistency. Out-of-sample predictive capacity requires additional validation.<\/p>\n<\/div>\n

\n
03. No exact timing<\/span><\/div>\n

A regime can remain in extreme territory for weeks or months. The signal identifies asymmetric risk conditions \u2014 not the entry moment. Requires technical or macro confirmation.<\/p>\n

\n<\/div>\n<\/div>\n<\/section>\n

\n
THIS WEEK’S SIGNAL \u00b7 $GLD<\/strong><\/div>\n