Pro­gram:

12:00-12:05
Open­ing
12:05-13:00
Fab­rizio Lillo (Uni­ver­sità di Bologna and Scuola Nor­male Su­pe­ri­ore, Pisa):
Mar­ket im­pact, slip­page costs, and op­ti­mal ex­e­cu­tion of large trades
13:00-13:30
György Ot­tuc­sák (Mor­gan Stan­ley, Bu­dapest):
Ma­chine Learn­ing in In­ter­est Rate Mar­kets
13:30-14:00
break
14:00-14:30
Mik­lós Rá­sonyi (Rényi In­sti­tute, ELTE, Bu­dapest):
Noisy sto­chas­tic gra­di­ents for price pre­dic­tion
14:30-15:00
Ujlaki Lev­ente, Szlávik Zsolt (Mor­gan Stan­ley, Bu­dapest):
Fixed In­come E-trad­ing Evo­lu­tion
15:00-16:00
Se­bas­t­ian Jaimun­gal (Uni­ver­sity of Toronto):
Al­go­rith­mic Trad­ing: Op­ti­mal Con­trol to Games to Re­in­force­ment Learn­ing

Se­bas­t­ian Jaimun­gal (Uni­ver­sity of Toronto)

Al­go­rith­mic Trad­ing: Op­ti­mal Con­trol to Games to Re­in­force­ment Learn­ing

There has been much work over the last two decades on how to trade in an op­ti­mal fash­ion on elec­tronic mar­kets. In this talk, I will pro­vide an overview of sev­eral as­pects of this class of prob­lems rang­ing over their for­mu­la­tions as sto­chas­tic con­trol prob­lems, to their gen­er­al­iza­tion to the many player set­ting where they may be ap­prox­i­mated as mean field games, and fi­nally how model-free re­in­force­ment learn­ing may play a role in nu­mer­i­cally solv­ing pre­vi­ously in­tractable prob­lems.

Fab­rizio Lillo (Uni­ver­sità di Bologna and Scuola Nor­male Su­pe­ri­ore, Pisa)

Mar­ket im­pact, slip­page costs, and op­ti­mal ex­e­cu­tion of large trades

Mar­ket im­pact is one of the most im­por­tant sources of trad­ing cost for fi­nan­cial in­vestors ex­e­cut­ing large or­ders. Nonethe­less its mea­sure­ment, mod­el­ing, and con­trol are still not fully un­der­stood. I will pre­sent some re­cent ad­vances on this topic, con­sid­er­ing both em­pir­i­cal as­pects, both in uni­vari­ate and in port­fo­lio set­ting, and mod­el­ing ap­proaches, con­sid­er­ing both re­duced form mod­esl and ap­proaches de­scrib­ing ex­plic­itly the limit or­der book dy­nam­ics. Fi­nally, I will dis­cuss the rel­e­vance of these find­ings for the prob­lem of op­ti­mal ex­e­cu­tion of large trades. Slides.

Mik­lós Rá­sonyi (Rényi In­sti­tute, ELTE, Bu­dapest)

Noisy sto­chas­tic gra­di­ents for price pre­dic­tion

We pre­sent new con­ver­gence re­sults for the so-called sto­chas­tic gra­di­ent Langevin al­go­rithm. Price pre­dic­tion is a po­ten­tial ap­pli­ca­tion. We also ex­plain some new re­search di­rec­tions in­volv­ing higher or­der reg­u­lar­iza­tion. Slides.

The work­shop is free for reg­is­tered par­tic­i­pants. You can reg­is­ter un­til Nov 19, 2021. If you want to can­cel your reg­is­tra­tion con­tact the or­ga­niz­ers at riskconf@ttk.elte.hu.

With my reg­is­tra­tion I give con­sent to and per­mit im­age- and sound-record­ing to be taken of me on the event, and these record­ings to be used by the or­ga­nizer(s) in their in­ter­nal and ex­ter­nal com­mu­ni­ca­tions (e.g. with aims as re­port­ing and giv­ing in­for­ma­tion about the event, prop­a­gat­ing/​pub­li­ciz­ing the event, us­ing them as ref­er­ence).

These record­ings of me can be used for the above men­tioned goals by any me­dia provider free of charge, with­out any place or time lim­i­ta­tion, through any tech­nol­ogy suit­able for broad­cast­ing to the pub­lic, with­out any lim­i­ta­tions re­gard­ing the num­ber of times be­ing used, and through every known uti­liza­tion method stated in the Act LXXVI of 1999 on Copy­right.

With my reg­is­tra­tion, I give per­mit to store and use my data dur­ing the or­ga­ni­za­tion of the cur­rent and fu­ture work­shops. These data will not be shared with any third par­ties.

Pro­gram com­mit­tee:

  • A. Zem­pléni (chair),
  • L. Márkus,
  • N.M. Arató,
  • J. Gáll,
  • Gy. Michalet­zky,
  • G. Mol­nár-Sáska,
  • V. Prokaj,
  • M. Rá­sonyi

Lo­cal or­gan­is­ers:

  • A. Zem­pléni (chair),
  • Á. Back­hausz,
  • V. Csiszár

email:

The main spon­sor is This work­shop is also sup­ported by
Registration form